Sensor diagnostic device and computer-readable recording medium

Abstract

The data acquisition unit (110) acquires a sensor data group from a sensor group (200) including a plurality of sensors of different types. The object detection unit (120) calculates a position information group for an object existing around the sensor group based on the acquired sensor data group. The environment determination unit (130) determines the surrounding environment of the sensor group based on at least any one of the acquired sensor data. The normal range determination unit (140) determines a normal range for the calculated position information group based on the determined environment. The state determination unit (150) determines the state of the sensor group based on the calculated position information group and the determined normal range.

Description

Technical Field

[0001] The present invention relates to a technology for diagnostic sensors. Background Art

[0002] Conventional anomaly diagnosis devices have been proposed as devices that can detect system abnormalities even when unknown anomalies occur.

[0003] In Patent Document 1, the following diagnostic device is disclosed. For this diagnostic device, a normal system model is created based on the sensor data when the system is normal and the relationships between multiple sensors. This diagnostic device compares the values of the relationships between the sensors calculated based on the current sensor data of each sensor with the values of the normal model. Further, this diagnostic device diagnoses as an anomaly when a deviation value is output, and determines that the system is abnormal in this case.

[0004] Prior Art Documents

[0005] Patent Documents

[0006] Patent Document 1: Japanese Patent Application Laid-Open No. 2014-148294 Summary of the Invention

[0007] Problems to be Solved by the Invention

[0008] Conventionally, a normal model is created based on the output values of sensors and the relationships between multiple sensors, and a diagnostic device performs anomaly diagnosis of sensors based on the degree of deviation indicating how much the correlation between the current multiple sensors differs from the correlation of the normal model.

[0009] However, it is considered that even if the sensors are normal, the magnitude of the deviation in measurement accuracy may vary depending on the surrounding environment such as weather (sunny, rainy, foggy, etc.) or time period (morning, noon, night, etc.).

[0010] Therefore, if the surrounding environment is not considered, an appropriate degree of deviation cannot be obtained, and thus the sensors cannot be correctly diagnosed.

[0011] An object of the present invention is to enable correct diagnosis considering the surrounding environment.

[0012] Means for Solving the Problems

[0013] The sensor diagnostic device of the present invention includes:

[0014] a data acquisition unit that acquires a sensor data group from a sensor group including a plurality of sensors of different types;

[0015] an object detection unit that calculates a position information group for an object existing around the sensor group based on the acquired sensor data group;

[0016] An environment determination unit that determines the surrounding environment of the sensor group based on at least any one of the acquired sensor data sets;

[0017] A normal range determination unit that determines a normal range for the calculated position information set based on the determined environment; and

[0018] A state determination unit that determines the state of the sensor group based on the calculated position information set and the determined normal range.

[0019] Advantages of the Invention

[0020] According to the present invention, accurate diagnosis taking into account the surrounding environment can be performed. Brief Description of the Drawings

[0021] Figure 1 is a structural diagram of the sensor diagnosis device 100 in Embodiment 1.

[0022] Figure 2 is a flowchart of the sensor diagnosis method in Embodiment 1.

[0023] Figure 3 is a flowchart of the normal range determination process (S140) in Embodiment 1.

[0024] Figure 4 is a flowchart of the state determination process (S150) in Embodiment 1.

[0025] Figure 5 is a diagram showing the error range of the position information in Embodiment 1.

[0026] Figure 6 is a flowchart of the parameter generation method in Embodiment 1.

[0027] Figure 7 is a diagram showing the normal distribution of the position information in Embodiment 1.

[0028] Figure 8 is a diagram showing the change in the deterioration degree of the sensor group 200 in Embodiment 1.

[0029] Figure 9 is a flowchart of the sensor diagnosis method in Embodiment 2.

[0030] Figure 10 is a flowchart of the normal range determination process (S240) in Embodiment 2.

[0031] Figure 11 is a flowchart of the state determination process (S250) in Embodiment 2.

[0032] Figure 12 It is a flowchart of the parameter generation method in Embodiment 2.

[0033] Figure 13 It is a diagram showing the principal components of the position information in Embodiment 2.

[0034] Figure 14 It is a diagram showing the normal distribution of the position feature quantity in Embodiment 2.

[0035] Figure 15 It is a comparison diagram of the position information distribution and the position feature quantity distribution in Embodiment 2.

[0036] Figure 16 It is a flowchart of the sensor diagnosis method in Embodiment 3.

[0037] Figure 17 It is a flowchart of the normal range determination process (S340) in Embodiment 3.

[0038] Figure 18 It is a diagram showing the relationship curve graph in Embodiment 3.

[0039] Figure 19 It is a diagram showing the approximate curve in Embodiment 3.

[0040] Figure 20 It is a flowchart of the sensor diagnosis method in Embodiment 4.

[0041] Figure 21 It is a flowchart of the normal range determination process (S440) in Embodiment 4.

[0042] Figure 22 It is a hardware structure diagram of the sensor diagnosis device 100 in the embodiment. Detailed Embodiment

[0043] In the embodiments and the drawings, the same reference numerals are assigned to the same elements or corresponding elements. The description of the elements with the same reference numerals as those already described is appropriately omitted or simplified. The arrows in the drawings mainly indicate the data flow or the processing flow.

[0044] Embodiment 1

[0045] Based on Figures 1 to 8 The sensor diagnosis device 100 will be described.

[0046] ***Description of the Structure***

[0047] Based on Figure 1 The structure of the sensor diagnosis device 100 will be described.

[0048] The sensor diagnosis device 100 is a computer for diagnosing the sensor group 200.

[0049] For example, the sensor diagnostic device 100 is mounted on a moving body together with the sensor group 200, and determines the state (normal or abnormal) of the sensor group 200 during the movement of the moving body or during the stop of the moving body. Specific examples of the moving body include an automobile, a robot, or a ship. The ECU mounted on the moving body may also function as the sensor diagnostic device 100.

[0050] ECU is an abbreviation for Electronic Control Unit.

[0051] The sensor group 200 includes a plurality of sensors of different types. A plurality of sensors of the same type may also be included in the sensor group 200.

[0052] Specific examples of the sensors are the camera 201, the LIDAR 202, the millimeter-wave radar 203, or the sonar 204.

[0053] The sensor group 200 is used to observe the surrounding environment and the objects present in the surroundings.

[0054] Specific examples of the environment are the weather (such as sunny, rainy, or foggy days) and the brightness. The brightness serves as a reference for time periods such as day or night. Additionally, the brightness serves as a reference for the presence or absence of backlighting. The object reflectivity in the measurements based on the LIDAR 202, the millimeter-wave radar 203, or the sonar 204 is also an example of the environment. These environments affect the field of view of each sensor. That is, these environments affect the measurements of each sensor.

[0055] Specific examples of the objects are other vehicles, pedestrians, or buildings.

[0056] The sensor diagnostic device 100 has hardware such as a processor 101, a memory 102, an auxiliary storage device 103, and an input / output interface 104. These hardware components are interconnected via signal lines.

[0057] The processor 101 is an IC that performs arithmetic processing and controls other hardware. For example, the processor 101 is a CPU, a DSP, or a GPU.

[0058] IC is an abbreviation for Integrated Circuit.

[0059] CPU is an abbreviation for Central Processing Unit.

[0060] DSP is an abbreviation for Digital Signal Processor.

[0061] The GPU is short for Graphics Processing Unit.

[0062] The memory 102 is a volatile or non-volatile storage device. The memory 102 is also referred to as the main storage device or main memory. For example, the memory 102 is a RAM. The data stored in the memory 102 is saved in the auxiliary storage device 103 as needed.

[0063] RAM is short for Random Access Memory.

[0064] The auxiliary storage device 103 is a non-volatile storage device. For example, the auxiliary storage device 103 is a ROM, HDD, or flash memory. The data stored in the auxiliary storage device 103 is loaded into the memory 102 as needed.

[0065] ROM is short for Read Only Memory.

[0066] HDD is short for Hard Disk Drive.

[0067] The input / output interface 104 is a port for connecting various devices. The sensor group 200 is connected to the input / output interface 104.

[0068] The sensor diagnostic device 100 has elements such as a data acquisition unit 110, an object detection unit 120, an environment determination unit 130, a normal range determination unit 140, and a status determination unit 150. These elements are implemented by software.

[0069] A sensor diagnostic program for causing a computer to function as the data acquisition unit 110, the object detection unit 120, the environment determination unit 130, the normal range determination unit 140, and the status determination unit 150 is stored in the auxiliary storage device 103. The sensor diagnostic program is loaded into the memory 102 and executed by the processor 101.

[0070] An OS is also stored in the auxiliary storage device 103. At least a part of the OS is loaded into the memory 102 and executed by the processor 101.

[0071] The processor 101 executes the sensor diagnostic program while executing the OS.

[0072] OS is short for Operating System.

[0073] The input / output data of the sensor diagnostic program is stored in the storage unit 190. For example, a parameter database 191, etc. is stored in the storage unit 190. The parameter database 191 will be described later.

[0074] The memory 102 functions as a storage unit 190. Among them, storage devices such as the auxiliary storage device 103, the registers in the processor 101, and the cache memory in the processor 101 can also function as the storage unit 190 instead of the memory 102, or function as the storage unit 190 together with the memory 102.

[0075] The sensor diagnostic device 100 may also have multiple processors that replace the processor 101. The multiple processors share the functions of the processor 101.

[0076] The sensor diagnostic program can be recorded (stored) in a non-volatile recording medium such as an optical disc or a flash memory in a computer-readable manner.

[0077] ***Description of the operation***

[0078] The steps of the operation of the sensor diagnostic device 100 correspond to the sensor diagnostic method. In addition, the steps of the operation of the sensor diagnostic device 100 correspond to the steps of the processing based on the sensor diagnostic program.

[0079] Each sensor in the sensor group 200 measures and outputs sensor data at each moment.

[0080] The camera 201 captures the surroundings at each moment and outputs image data. The image data is data of the captured image of the surroundings.

[0081] The LIDAR 202 irradiates laser light to the surroundings at each moment and outputs point cloud data. The point cloud data represents a distance vector and a reflection intensity for each location where the laser light is reflected.

[0082] The millimeter-wave radar 203 transmits millimeter waves to the surroundings at each moment and outputs distance data. The distance data represents a distance vector for each location where the millimeter waves are reflected.

[0083] The sonar 204 transmits sound waves to the surroundings at each moment and outputs distance data. The distance data represents a distance vector for each location where the sound waves are reflected.

[0084] The image data, the point cloud data, and the distance data are each an example of sensor data.

[0085] Based on Figure 2 , the sensor diagnostic method is described.

[0086] Steps S110 to S150 are executed at each moment. That is, steps S110 to S150 are repeatedly executed.

[0087] In step S110, the data acquisition unit 110 acquires a sensor data group from the sensor group 200.

[0088] That is, the data acquisition unit 110 acquires sensor data from each sensor of the sensor group 200.

[0089] In step S120, the object detection unit 120 calculates a group of position information of the object based on the sensor data group.

[0090] The group of position information of the object is one or more pieces of position information with respect to the object.

[0091] The position information of the object is information for identifying the position of the object. Specifically, the position information is a coordinate value. For example, the position information is a coordinate value in a local coordinate system, that is, a coordinate value for identifying a relative position with respect to the sensor group 200. The coordinate value can be a one-dimensional value (x), a two-dimensional value (x, y), or a three-dimensional value (x, y, z).

[0092] The group of position information of the object is calculated as follows.

[0093] The object detection unit 120 performs data processing for each sensor data. Thus, the object detection unit 120 detects the object for each sensor data and calculates the coordinate value of the object. At this time, in order to perform the detection of the object and the calculation of the coordinate value of the object, the conventional data processing can be used according to the type of sensor data.

[0094] In the case where multiple objects are detected, each object is identified and the coordinate value of each object is calculated.

[0095] At least one piece of position information can be calculated by sensor fusion. In sensor fusion, there are various methods such as early fusion, cross fusion, and late fusion. In addition, as combinations of sensors, various combinations such as the camera 201 and the LIDAR 202, the LIDAR 202 and the millimeter wave radar 203, and the camera 201 and the millimeter wave radar 203 can be considered.

[0096] In the case of using sensor fusion, the object detection unit 120 uses two or more pieces of sensor data obtained from two or more sensors to calculate one piece of position information. The method of sensor fusion used for this calculation is arbitrary. For example, the object detection unit 120 calculates the position information for each sensor data and calculates the average value of the calculated position information. The calculated average value is used as the position information calculated by sensor fusion.

[0097] In step S130, the environment determination unit 130 determines the environment based on at least one piece of sensor data.

[0098] The environment is determined as follows.

[0099] First, the environment determination unit 130 selects one sensor.

[0100] Next, the environment determination unit 130 processes the sensor data obtained from the selected sensor. At this time, in order to determine the environment, past data processing can be used according to the type of sensor data.

[0101] Then, the environment determination unit 130 determines the environment based on the result of the data processing.

[0102] One sensor is selected as follows.

[0103] The environment determination unit 130 selects a pre-determined sensor. The environment determination unit 130 may also select a sensor based on the previous environment. For example, the environment determination unit 130 can use a sensor table to select a sensor corresponding to the previous environment. The sensor table is a table that correlates the environment with the sensors and is pre-stored in the storage unit 190.

[0104] The environment can also be determined by sensor fusion. In sensor fusion, there are various methods such as early fusion, cross fusion, and late fusion. In addition, as combinations of sensors, various combinations such as the camera 201 and the LIDAR 202, the LIDAR 202 and the millimeter-wave radar 203, and the camera 201 and the millimeter-wave radar 203 can be considered.

[0105] In this case, the environment determination unit 130 selects two or more sensors and uses two or more sensor data obtained from the selected two or more sensors to determine the environment. The method of sensor fusion used for this determination is arbitrary. For example, the environment determination unit 130 determines the environment for each sensor data and decides the environment based on the majority vote of the determination results.

[0106] In step S140, the normal range determination unit 140 determines the normal range based on the environment determined in step S130.

[0107] The normal range is the range of normal position information. When the sensor group 200 is normal, each position information calculated in step S120 converges to the normal range.

[0108] When multiple objects are detected in step S120, the normal range is determined for each object.

[0109] Based on Figure 3 , the steps of the normal range determination process (S140) will be described.

[0110] In step S141, the normal range determination unit 140 selects an arbitrary sensor based on the environment determined in step S130.

[0111] For example, the normal range determination unit 140 uses a sensor table to select a sensor corresponding to the environment. The sensor table is a table that correlates the environment with the sensors and is pre-stored in the storage unit 190.

[0112] In step S142, the normal range determination unit 140 selects, from the position information group calculated in step S120, the position information corresponding to the sensor selected in step S141.

[0113] That is, the normal range determination unit 140 selects the position information calculated using the sensor data obtained from the selected sensor.

[0114] In step S143, the normal range determination unit 140 obtains, from the parameter database 191, the range parameter corresponding to the environment determined in step S130 and the position information selected in step S142.

[0115] The range parameter is a parameter used to determine the normal range.

[0116] In the parameter database 191, the range parameters are registered for each combination of the environment information and the position information.

[0117] For example, the normal range determination unit 140 obtains, from the parameter database 191, the range parameter corresponding to the environment information indicating the environment determined in step S130 and the position information of the position closest to the position identified by the position information selected in step S142.

[0118] In step S144, the normal range determination unit 140 calculates the normal range using the range parameter obtained in step S143.

[0119] The normal range is calculated as follows.

[0120] The range parameter represents the distribution of the normal position information. For example, the range parameter is the average value of the normal position information and the standard deviation (σ) of the normal position information.

[0121] The normal range determination unit 140 calculates the normal range based on the distribution of the normal position information. For example, the normal range determination unit 140 calculates the range of the average value ± 2σ. The calculated range is the normal range. However, "1σ" or "3σ" etc. can also be used instead of "2σ".

[0122] Return Figure 2 , and step S150 will be described.

[0123] In step S150, the state determination unit 150 determines the state of the sensor group 200 based on the position information group calculated in step S120 and the normal range determined in step S140.

[0124] Based on Figure 4 , the steps of the status determination process (S150) will be described.

[0125] In step S151, the status determination unit 150 compares each position information calculated in step S120 with the normal range determined in step S140.

[0126] Then, based on the comparison result, the status determination unit 150 determines whether each position information calculated in step S120 is included in the normal range determined in step S140.

[0127] When multiple objects are detected in step S120, the status determination unit 150 determines whether each position information is included in the normal range for each object.

[0128] In step S152, the status determination unit 150 stores the determination result obtained in step S151 in the storage unit 190.

[0129] In step S153, the status determination unit 150 determines whether a predetermined time has elapsed. This predetermined time is a time determined in advance for the status determination process (S150).

[0130] For example, the status determination unit 150 determines whether a new predetermined time has elapsed since the last moment when the predetermined time has elapsed.

[0131] When the predetermined time has elapsed, the process proceeds to step S154.

[0132] When the predetermined time has not elapsed, the status determination process (S150) ends.

[0133] In step S154, the status determination unit 150 uses the determination results stored in step S152 during the predetermined time to calculate the ratio of the position information outside the normal range.

[0134] In step S155, the status determination unit 150 determines the status of the sensor group 200 based on the ratio of the position information outside the normal range.

[0135] When it is determined that the sensor group 200 is abnormal, it can be considered that at least any one of the sensors in the sensor group 200 is abnormal.

[0136] The status of the sensor group 200 is determined as follows.

[0137] The status determination unit 150 compares the ratio of the position information outside the normal range with a ratio threshold. This ratio threshold is a threshold determined in advance for the status determination process (S150).

[0138] When the proportion of position information outside the normal range is greater than the proportion threshold, the state determination unit 150 determines that the sensor group 200 is abnormal.

[0139] When the proportion of position information outside the normal range is less than the proportion threshold, the state determination unit 150 determines that the sensor group 200 is normal.

[0140] When the proportion of position information outside the normal range is equal to the proportion threshold, the state determination unit 150 may determine that the sensor group 200 is abnormal or may determine that the sensor group 200 is normal.

[0141] ***Supplement to Embodiment 1***

[0142] Regarding the parameter database 191, the following is a supplement.

[0143] Figure 5 Represents the error range of the position information of the object detected by the normal sensor group 200. For example, the sensor group 200 is mounted on an automobile.

[0144] The range of the shaded area marked for each intersection point represents the error range of the position information of the object detected by the normal sensor group 200 when the object is located at the intersection point.

[0145] Even if the sensor group 200 is normal, there will be errors in the measurement of the sensor group 200. Therefore, errors occur in the position information group calculated based on the sensor data group. And the size of the error range varies according to the position of the object. For example, it can be considered that the farther the position of the object is, the larger the error range is. In addition, it can be considered that the size of the error range also varies according to the environment (such as weather or brightness, etc.).

[0146] In the sensor diagnosis method, the normal range corresponds to the error range. By determining the normal range based on the surrounding environment and the position information of the object, the state of the sensor group 200 can be accurately determined.

[0147] In the parameter database 191, range parameters are registered for each combination of environmental information and position information.

[0148] Based on Figure 6 , the parameter generation method will be described.

[0149] The parameter generation method is a method for generating range parameters.

[0150] In the following description, an "operator" is a person who performs operations for implementing the parameter generation method. A "computer" is a device for generating range parameters (parameter generation device). A "sensor group" is the same sensor group as the sensor group 200, or a sensor group of the same type as the sensor group 200.

[0151] In step S1901, the operator configures a sensor group and connects the sensor group to a computer.

[0152] In step S1902, the operator determines the position of an object and places the object at the determined position.

[0153] In step S1903, the operator inputs environmental information for identifying the environment of the place into the computer. Additionally, the operator inputs position information for identifying the position where the object is placed into the computer.

[0154] In step S1911, each sensor of the sensor group makes measurements.

[0155] Step S1912 is the same as step S110.

[0156] In step S1912, the computer obtains a sensor data group from the sensor group.

[0157] Step S1913 is the same as step S120.

[0158] In step S1913, the computer calculates a position information group of the object based on the sensor data group.

[0159] In step S1914, the computer stores the position information group of the object.

[0160] In step S1915, the computer determines whether the observation time has elapsed. The observation time is a time predetermined for the parameter generation method.

[0161] For example, the computer determines whether the observation time has elapsed since the moment when the sensor data group was first obtained from the sensor group in step S1912.

[0162] If the observation time has elapsed, the process proceeds to step S1921.

[0163] If the observation time has not elapsed, the process proceeds to step S1911.

[0164] In step S1921, the computer calculates range parameters based on one or more position information groups stored in step S1914 during the observation time.

[0165] The range parameters are calculated as follows.

[0166] First, the computer calculates a normal distribution for one or more position information groups.

[0167] Then, the computer calculates the mean value in the calculated normal distribution. Further, the computer calculates the standard deviation in the calculated normal distribution. The combination of the calculated mean value and the calculated standard deviation forms a range parameter.

[0168] However, the computer can also calculate a probability distribution other than the normal distribution. In addition, the computer can also calculate a range parameter different from the combination of the mean value and the standard deviation.

[0169] Figure 7 Represents the relationship between multiple position information, the normal distribution (x), and the normal distribution (y).

[0170] Multiple pieces of position information form one or more position information groups.

[0171] One white circle represents one piece of position information. Specifically, the white circle represents two-dimensional coordinate values (x, y). The normal distribution (x) is the normal distribution at the x coordinate. The normal distribution (y) is the normal distribution at the y coordinate.

[0172] For example, the computer calculates the normal distribution (x) and the normal distribution (y) for multiple pieces of position information. Then, the computer calculates the combination of the mean value and the standard deviation for the normal distribution (x) and the normal distribution (y) respectively.

[0173] Return Figure 6 , and explains step S1922.

[0174] In step S1922, the computer stores the range parameter calculated in step S1921 corresponding to the environmental information input in step S1903 and the position information input in step S1903.

[0175] The parameter generation method is executed for each combination of the surrounding environment and the position of the object. Thus, range parameters are obtained for each combination of the surrounding environment and the position of the object.

[0176] Then, each range parameter is registered in the parameter database 191 corresponding to the environmental information and the position information.

[0177] ***Effect of Embodiment 1***

[0178] The sensor diagnostic device 100 can determine an appropriate normal range according to the surrounding environment and the position of the object. As a result, the sensor diagnostic device 100 has the effect of being able to more accurately determine the state of the sensor group 200.

[0179] ***Example of Embodiment 1***

[0180] Different range parameters can also be used according to the type of object. In this case, Embodiment 1 is implemented as follows. The differences from the above description will be mainly described.

[0181] The parameter generation method (refer to Figure 6 ) is implemented for each combination of the surrounding environment, the position of the object, and the type of the object.

[0182] In step S1903, the operator inputs the environmental information, position information, and type information into the computer. The type information identifies the type of the object.

[0183] In step S1922, the computer stores the range parameters corresponding to the environmental information, position information, and type information.

[0184] The sensor diagnosis method (refer to Figure 2 ) will be described.

[0185] In step S120, the object detection unit 120 calculates a group of position information of the object based on the sensor data group. And the object detection unit 120 determines the type of the object based on at least one sensor data. The type of the object is determined as follows. The object detection unit 120 selects one sensor data, performs data processing on the selected sensor data, and determines the type of the object according to the result of the data processing. At this time, in order to determine the type of the object, the past data processing can be used according to the type of the sensor data. For example, the object detection unit 120 determines the type of the object captured in the image by performing image processing using the image data. The type of the object can also be determined by sensor fusion. In this case, the object detection unit 120 uses two or more sensor data to determine the type of the object. The method of sensor fusion used for this determination is arbitrary. For example, the object detection unit 120 determines the type of the object according to each sensor data, and determines the type of the object by majority voting of the determination results.

[0186] In step S140, the normal range determination unit 140 determines the normal range based on the surrounding environment and the type of the object. Based on Figure 3 , the normal range determination process (S140) will be described.

[0187] In step S141, the normal range determination unit 140 selects an arbitrary sensor based on the surrounding environment and the type of the object. For example, the normal range determination unit 140 uses a sensor table and selects a sensor corresponding to the surrounding environment and the type of the object. The sensor table is a table in which a group of the environment and the type of the object are corresponded to the sensors, and is pre-stored in the storage unit 190.

[0188] In step S143, the normal range determination unit 140 obtains range parameters corresponding to the surrounding environment, the type of object, and the position information from the parameter database 191.

[0189] The state determination unit 150 may also calculate the ratio of the position information within the normal range.

[0190] The state determination unit 150 may also determine the degree of deterioration of the sensor group 200 based on the ratio of the position information within the normal range or the ratio of the position information outside the normal range. The degree of deterioration of the sensor group 200 is an example of the information indicating the state of the sensor group 200.

[0191] The state determination unit 150 may determine the degree of deterioration of the sensor group 200 while determining the normality or abnormality of the sensor group 200, or may determine the degree of deterioration of the sensor group 200 instead of determining the normality or abnormality of the sensor group 200.

[0192] Figure 8 Shows the change in the degree of deterioration of the sensor group 200.

[0193] It is considered that the sensor group 200 deteriorates over time. That is, it is considered that the degree of deterioration of the sensor group 200 changes in the order of "no deterioration", "slight deterioration", "moderate deterioration", and "severe deterioration (abnormal)".

[0194] The white circles represent the position information groups when the degree of deterioration of the sensor group 200 is "no deterioration". For example, when the ratio of the position information within the normal range is 100%, the degree of deterioration of the sensor group 200 is "no deterioration".

[0195] The white triangles represent the position information groups when the degree of deterioration of the sensor group 200 is "slight deterioration". For example, when the ratio of the position information within the normal range is 80% or more and less than 100%, the degree of deterioration of the sensor group 200 is "slight deterioration".

[0196] The black triangles represent the position information groups when the degree of deterioration of the sensor group 200 is "moderate deterioration". For example, when the ratio of the position information within the normal range is 40% or more and less than 80%, the degree of deterioration of the sensor group 200 is "moderate deterioration".

[0197] The crosses represent the position information groups when the degree of deterioration of the sensor group 200 is "severe deterioration (abnormal)". For example, when the ratio of the position information within the normal range is less than 40%, the degree of deterioration of the sensor group 200 is "severe deterioration (abnormal)".

[0198] Each marker representing the position information group gradually moves outward from the center of the normal range (the dotted circle).

[0199] The state determination unit 150 may also determine the state (normal or abnormal) of each sensor set composed of two or more sensors included in the sensor group 200, and determine the abnormal sensors based on the state of each sensor set.

[0200] For example, assume that the set of the camera 201 and the LIDAR 202 is normal, and the set of the camera 201 and the millimeter-wave radar 203 is abnormal. In this case, the state determination unit 150 determines that the millimeter-wave radar 203 is abnormal.

[0201] That is, in the case where there is a normal sensor set and an abnormal sensor set, the state determination unit 150 determines that the sensor included in the abnormal sensor set and not included in the normal sensor set is abnormal.

[0202] Embodiment 2

[0203] Regarding the method of determining the state of the sensor group 200 using the feature amount related to the position information of the object, mainly based on Figures 9 to 15 explain the differences from Embodiment 1.

[0204] ***Description of the structure***

[0205] The structure of the sensor diagnostic device 100 is the same as the structure in Embodiment 1 (refer to Figure 1 ).

[0206] ***Description of the operation***

[0207] Based on Figure 9 , explain the sensor diagnostic method.

[0208] Steps S210 to S250 correspond to steps S110 to S150 in Embodiment 1 (refer to Figure 2 ).

[0209] Steps S210 to S230 are the same as steps S110 to S130 in Embodiment 1.

[0210] In step S240, the normal range determination unit 140 determines the normal range based on the environment determined in step S230.

[0211] Based on Figure 10 , explain the steps of the normal range determination process (S240).

[0212] Steps S241 to S244 correspond to steps S141 to S144 in Embodiment 1 (refer to Figure 3 ).

[0213] Steps S241 to S243 are the same as steps S141 to S143 in Embodiment 1.

[0214] In step S244, the normal range determination unit 140 calculates the normal range using the range parameter obtained in step S243.

[0215] The feature amount of the position information is referred to as the position feature amount.

[0216] The normal range is the range of the feature amounts of the normal position information, that is, the range of the normal position feature amounts.

[0217] The position feature amount is given to the position information of the object by the feature extraction method.

[0218] A specific example of the feature extraction method is principal component analysis.

[0219] A specific example of the position feature amount is the feature amount based on principal component analysis, that is, the principal component score.

[0220] The principal component score can be one value with respect to one principal component, or two or more values with respect to two or more principal components.

[0221] The normal range is calculated as follows.

[0222] The range parameter represents the distribution of the normal position feature amounts. For example, the range parameter is the average value of the normal position feature amounts and the standard deviation (σ) of the normal position feature amounts.

[0223] The normal range determination unit 140 calculates the normal range based on the distribution of the normal position feature amounts. For example, the normal range determination unit 140 calculates the range of the average value ± 2σ. The calculated range is the normal range. However, "1σ" or "3σ" etc. can also be used instead of "2σ".

[0224] Return Figure 9 , and step S250 will be described.

[0225] In step S250, the state determination unit 150 determines the state of the sensor group 200 based on the position information group calculated in step S220 and the normal range determined in step S240.

[0226] Based on Figure 11 , the steps of the state determination process (S250) will be described.

[0227] Steps S252 to S256 correspond to steps S151 to S155 in Embodiment 1 (refer to Figure 4 ).

[0228] In step S251, the state determination unit 150 calculates a position feature amount, which is a feature amount of each position information calculated in step S220.

[0229] When a plurality of objects are detected in step S220, the state determination unit 150 calculates the position feature amount for each position information for each object.

[0230] A specific example of the position feature amount is the principal component score. The principal component score is calculated as follows.

[0231] In the parameter database 191, a range parameter and a conversion formula are registered for each combination of the environment information and the position information.

[0232] The conversion formula is a formula for converting the position information into the principal component score, and is represented by a matrix, for example.

[0233] First, the state determination unit 150 acquires the conversion formula registered together with the range parameter selected in step S243 from the parameter database 191.

[0234] Then, the state determination unit 150 substitutes the position information into the conversion formula and calculates the conversion formula. Thereby, the principal component score is calculated.

[0235] However, it is also possible to calculate a position feature amount of a type different from the principal component score.

[0236] In step S252, the state determination unit 150 compares each position feature amount calculated in step S251 with the normal range determined in step S240.

[0237] Then, the state determination unit 150 determines, based on the comparison result, whether each position feature amount calculated in step S251 is included in the normal range determined in step S240.

[0238] When a plurality of objects are detected in step S220, the state determination unit 150 determines whether each position feature amount is included in the normal range for each object.

[0239] In step S253, the state determination unit 150 stores the determination result obtained in step S252 in the storage unit 190.

[0240] In step S254, the state determination unit 150 determines whether a predetermined time has elapsed. The predetermined time is a time determined in advance for the state determination process (S250).

[0241] For example, the state determination unit 150 determines whether a new predetermined time has elapsed since the last time when the predetermined time has elapsed.

[0242] When the predetermined time has elapsed, the process proceeds to step S255.

[0243] The state determination process (S250) ends without passing the specified time.

[0244] In step S255, the state determination unit 150 calculates the ratio of the position feature amounts outside the normal range using the determination results stored in step S253 during the specified time.

[0245] In step S256, the state determination unit 150 determines the state of the sensor group 200 based on the ratio of the position feature amounts outside the normal range.

[0246] The state of the sensor group 200 is determined as follows.

[0247] The state determination unit 150 compares the ratio of the position feature amounts outside the normal range with a ratio threshold. This ratio threshold is a threshold determined in advance for the state determination process (S250).

[0248] When the ratio of the position feature amounts outside the normal range is greater than the ratio threshold, the state determination unit 150 determines that the sensor group 200 is abnormal.

[0249] When the ratio of the position feature amounts outside the normal range is less than the ratio threshold, the state determination unit 150 determines that the sensor group 200 is normal.

[0250] When the ratio of the position feature amounts outside the normal range is equal to the ratio threshold, the state determination unit 150 may determine that the sensor group 200 is abnormal or may determine that the sensor group 200 is normal.

[0251] ***Supplement of Embodiment 2***

[0252] Based on Figure 12 , the parameter generation method will be described.

[0253] Steps S2901 to S2903 are the same as steps S1901 to S1903 in Embodiment 1.

[0254] Steps S2911 to S2915 are the same as steps S1911 to S1915 in Embodiment 1.

[0255] In step S2921, the computer calculates one or more groups of position feature amounts for one or more groups of position information stored in step S2914 during the observation time. That is, the computer calculates the feature amounts (position feature amounts) of each position information.

[0256] A specific example of the position feature amount is the principal component score. The principal component score is calculated as follows.

[0257] First, the computer determines the principal components by performing principal component analysis on the position information groups.

[0258] Then, the computer calculates the principal component scores of each position information with respect to the determined principal components.

[0259] However, it is also possible to calculate position feature quantities of a different type from the principal component scores.

[0260] Figure 13 Shows the relationship between multiple position information, the first principal component, and the second principal component.

[0261] Multiple position information constitutes one or more position information groups.

[0262] One cross represents one position information. The position information is two-dimensional coordinate values (x, y).

[0263] For example, the computer determines the first principal component and the second principal component respectively by performing principal component analysis on multiple position information. Then, the computer calculates the first principal component score and the second principal component score for each position information. The first principal component score is the score (coordinate value) of the position information in the first principal component. The second principal component score is the score (coordinate value) of the position information in the second principal component.

[0264] Return Figure 12 , continue the description from step S2922.

[0265] In step S2922, the computer calculates the range parameter based on one or more position feature quantity groups calculated in step S2921.

[0266] The range parameter is calculated as follows.

[0267] First, the computer calculates the normal distribution for one or more position feature quantity groups.

[0268] Then, the computer calculates the mean in the calculated normal distribution. Furthermore, the computer calculates the standard deviation in the calculated normal distribution. The group consisting of the calculated mean and the calculated standard deviation is the range parameter.

[0269] However, the computer can also calculate a probability distribution other than the normal distribution. In addition, the computer can also calculate a range parameter different from the group of the mean and the standard deviation.

[0270] Figure 14 Shows the relationship between multiple position feature quantities, the normal distribution (a), and the normal distribution (b).

[0271] Multiple position feature quantities constitute one or more position feature quantity groups.

[0272] A cross represents a position feature quantity. Specifically, a cross represents two-dimensional feature quantities (a, b). The feature quantity (a) is the first principal component score, and the feature quantity (b) is the second principal component score. The normal distribution (a) is the normal distribution in the first principal component. The normal distribution (b) is the normal distribution in the second principal component.

[0273] For example, the computer calculates the normal distribution (a) and the normal distribution (b) for a plurality of position feature quantities. Then, the computer calculates groups of the mean value and the standard deviation for the normal distribution (a) and the normal distribution (b) respectively.

[0274] Return Figure 12 , and illustrate step S2923.

[0275] In step S2923, the computer stores the range parameter calculated in step S2922 corresponding to the environment information input in step S2903 and the position information input in step S2903.

[0276] ***Effects of Embodiment 2***

[0277] The sensor diagnostic device 100 can use the feature quantities related to the position information of the object to determine the state of the sensor group 200. As a result, the sensor diagnostic device 100 has the effect of being able to more accurately determine the state of the sensor group 200.

[0278] Figure 15 Show the distribution of the position information and the distribution of the position feature quantities.

[0279] The white circles represent normal position information or normal position feature quantities.

[0280] The crosses represent abnormal position information or abnormal position feature quantities.

[0281] The solid lines represent the normal distribution (normal distribution) of normal position information or normal position feature quantities.

[0282] The dashed lines represent the normal distribution (abnormal distribution) of abnormal position information or abnormal position feature quantities.

[0283] As Figure 15 shown, the difference between the distribution of normal position feature quantities and the distribution of abnormal position feature quantities is larger than the difference between the distribution of normal position information and the distribution of abnormal position information. Therefore, it is easier to distinguish between the normal position feature quantity group and the abnormal position feature quantity group than to distinguish between the normal position information group and the abnormal position information group.

[0284] Therefore, by using the position feature quantities, the state of the sensor group 200 can be determined more accurately.

[0285] ***Examples of Embodiment 2***

[0286] Similar to the example of Embodiment 1, different range parameters can also be used according to the type of object.

[0287] The state determination unit 150 can also calculate the ratio of the position feature amounts within the normal range.

[0288] The state determination unit 150 can also determine the degree of deterioration of the sensor group 200 based on the ratio of the position feature amounts within the normal range or the ratio of the position feature amounts outside the normal range. The degree of deterioration of the sensor group 200 is an example of the information indicating the state of the sensor group 200.

[0289] The state determination unit 150 can determine the degree of deterioration of the sensor group 200 while determining the normality or abnormality of the sensor group 200, or can determine the degree of deterioration of the sensor group 200 instead of determining the normality or abnormality of the sensor group 200.

[0290] Similar to the example of Embodiment 1, the state determination unit 150 can also identify the abnormal sensors based on the state of each sensor set.

[0291] Embodiment 3

[0292] Regarding the method of calculating the range parameters by using the parameter calculation formula, the differences from Embodiment 1 will be mainly described based on Figures 16 to 19 the differences from Embodiment 1 will be mainly described.

[0293] ***Description of Structure***

[0294] The structure of the sensor diagnostic device 100 is the same as the structure in Embodiment 1 (refer to Figure 1 ).

[0295] However, in the parameter database 191, the parameter calculation formulas are registered for each environmental information, instead of registering the range parameters for each combination of environmental information and position information. The parameter calculation formula is a formula for calculating the range parameters.

[0296] ***Description of Operation***

[0297] Based on Figure 16 this, the sensor diagnostic method will be described.

[0298] Steps S310 to S350 correspond to steps S110 to S150 in Embodiment 1 (refer to Figure 2 ).

[0299] Steps S310 to S330 are the same as steps S110 to S130 in Embodiment 1.

[0300] In step S340, the normal range determination unit 140 determines the normal range based on the environment determined in step S330.

[0301] Based on Figure 17 , the steps of the normal range determination process (S340) are described.

[0302] Step S341 corresponds to step S141 of Embodiment 1.

[0303] In step S341, the normal range determination unit 140 selects an arbitrary sensor based on the environment determined in step S330.

[0304] Step S342 corresponds to step S142 in Embodiment 1.

[0305] In step S342, the normal range determination unit 140 selects the position information corresponding to the sensor selected in step S341 from the position information group calculated in step S320.

[0306] In step S343, the normal range determination unit 140 obtains the parameter calculation formula corresponding to the environment determined in step S330 from the parameter database 191.

[0307] In step S344, the normal range determination unit 140 calculates the parameter calculation formula obtained in step S343, and calculates the range parameter corresponding to the position information selected in step S342.

[0308] The range parameter is calculated as follows.

[0309] The normal range determination unit 140 substitutes the position information into the parameter calculation formula and calculates the parameter calculation formula. Thereby, the range parameter corresponding to the position information is calculated.

[0310] Figure 18 A relationship curve graph is shown.

[0311] The relationship curve graph represents the relationship between the distance to the object and the deviation of the position information. The formula representing the relationship curve graph is equivalent to the parameter calculation formula.

[0312] The distance to the object is related to the position information of the object. That is, the distance to the object is equivalent to the position information of the object.

[0313] The deviation of the position information represents the range size of the normal position information. That is, the deviation of the position information is equivalent to the range parameter.

[0314] Return Figure 17 , the description of step S345 is given.

[0315] Step S345 corresponds to step S144 in Embodiment 1.

[0316] In step S345, the normal range determination unit 140 calculates the normal range using the range parameter calculated in step S344.

[0317] Return Figure 16 , and explain step S350.

[0318] Step S350 is the same as step S150 in Embodiment 1.

[0319] ***Supplement of Embodiment 3***

[0320] Explain the method for calculating the generation parameter formula.

[0321] Execute the parameter generation method for each combination of the surrounding environment and the position of the object (refer to Figure 6 ). Thus, range parameters are obtained for each combination of the environmental information and the position information.

[0322] The computer generates a relational expression between the position information and the range parameter according to each environmental information. The generated relational expression is used as the parameter calculation formula.

[0323] Figure 19 Show the approximate curve.

[0324] The white circles represent the position information.

[0325] The approximate curve represents the relationship between the "distance to the object" based on each position information and the "deviation" of each position information.

[0326] The parameter calculation formula corresponds to the formula (approximate formula) representing the approximate curve.

[0327] ***Effects of Embodiment 3***

[0328] The sensor diagnostic device 100 calculates the range parameter by calculating the parameter calculation formula, and uses the calculated range parameter to calculate the normal range. Thus, the sensor diagnostic device 100 can determine a more appropriate normal range. As a result, the sensor diagnostic device 100 has the effect of being able to more accurately determine the state of the sensor group 200.

[0329] ***Examples of Embodiment 3***

[0330] Different range parameters may also be used according to the type of the object. In this case, Embodiment 3 is implemented as follows. The differences from the above description will be mainly explained.

[0331] Execute the parameter generation method for each combination of the surrounding environment, the position of the object, and the type of the object (refer to Figure 6 ).

[0332] In step S1903, the operator inputs environmental information, location information, and type information into the computer. The type information identifies the type of the object.

[0333] In step S1922, the computer stores range parameters corresponding to the environmental information, location information, and type information.

[0334] Then, the computer generates a relational expression between the location information and the range parameters for each combination of the environmental information and the type information. The generated relational expression is used as a parameter calculation formula.

[0335] A sensor diagnosis method (refer to Figure 16 ) will be described.

[0336] In step S320, the object detection unit 120 calculates a set of location information of the object based on the set of sensor data. And, the object detection unit 120 determines the type of the object based on at least one sensor data. The type of the object is determined as follows. The object detection unit 120 selects one sensor data, performs data processing on the selected sensor data, and determines the type of the object according to the result of the data processing. At this time, in order to determine the type of the object, past data processing can be used according to the type of the sensor data. For example, the object detection unit 120 determines the type of the object captured in the image by performing image processing using the image data. The type of the object can also be determined by sensor fusion. In this case, the object detection unit 120 uses two or more sensor data to determine the type of the object. The method of sensor fusion used for this determination is arbitrary. For example, the object detection unit 120 determines the type of the object according to each sensor data, and decides the type of the object by a majority vote of the determination results.

[0337] In step S340, the normal range determination unit 140 determines the normal range based on the surrounding environment and the type of the object. Based on Figure 17 , the normal range determination process (S340) will be described.

[0338] In step S341, the normal range determination unit 140 selects an arbitrary sensor based on the surrounding environment and the type of the object. For example, the normal range determination unit 140 uses a sensor table and selects a sensor corresponding to the surrounding environment and the type of the object. The sensor table is a table in which a set of the environment and the type of the object and the sensors are corresponded to each other, and is pre-stored in the storage unit 190.

[0339] In step S343, the normal range determination unit 140 obtains a parameter calculation formula corresponding to the surrounding environment and the type of the object from the parameter database 191.

[0340] Similar to the embodiment of Embodiment 1, the state determination unit 150 may also determine the degree of deterioration of the sensor group 200 based on the ratio of the position information within the normal range or the ratio of the position information outside the normal range.

[0341] Similar to the embodiment of Embodiment 1, the state determination unit 150 may also determine the abnormal sensors based on the state of each sensor set.

[0342] Embodiment 4

[0343] Regarding the method of calculating the range parameter by the parameter calculation formula, it is mainly based on Figure 20 and Figure 21 to illustrate the differences from Embodiment 2.

[0344] ***Description of the structure***

[0345] The structure of the sensor diagnostic device 100 is the same as the structure in Embodiment 1 (refer to Figure 1 ).

[0346] However, in the parameter database 191, the parameter calculation formulas are registered according to each environmental information, rather than registering the range parameters according to each combination of environmental information and position information. The parameter calculation formula is a formula for calculating the range parameter.

[0347] ***Description of the operation***

[0348] Based on Figure 20 , the sensor diagnostic method will be described.

[0349] Steps S410 to S450 correspond to steps S210 to S250 in Embodiment 2 (refer to Figure 9 ).

[0350] Steps S410 to S430 are the same as steps S210 to S230 in Embodiment 2.

[0351] In step S440, the normal range determination unit 140 determines the normal range based on the environment determined in step S430.

[0352] Based on Figure 21 , the steps of the normal range determination process (S440) will be described.

[0353] Step S441 corresponds to step S241 of Embodiment 2.

[0354] In step S441, the normal range determination unit 140 selects an arbitrary sensor based on the environment determined in step S430.

[0355] Step S442 is equivalent to step S242 in Embodiment 2.

[0356] In step S442, the normal range determination unit 140 selects the position information corresponding to the sensor selected in step S441 from the group of position information calculated in step S420.

[0357] In step S443, the normal range determination unit 140 obtains the parameter calculation formula corresponding to the environment determined in step S430 from the parameter database 191.

[0358] In step S444, the normal range determination unit 140 calculates the parameter calculation formula obtained in step S443, and calculates the range parameter corresponding to the position information selected in step S442.

[0359] The range parameter is calculated as follows.

[0360] The normal range determination unit 140 substitutes the position information into the parameter calculation formula and calculates the parameter calculation formula. Thereby, the range parameter corresponding to the position information is calculated.

[0361] Step S445 is equivalent to step S244 in Embodiment 2.

[0362] In step S445, the normal range determination unit 140 calculates the normal range using the range parameter calculated in step S444.

[0363] Return Figure 20 , and describe step S450.

[0364] Step S450 is the same as step S250 in Embodiment 2.

[0365] ***Supplement of Embodiment 4***

[0366] Describe the method for generating the parameter calculation formula.

[0367] Execute the parameter generation method for each combination of the surrounding environment and the position of the object (refer to Figure 12 ). Thereby, range parameters are obtained for each combination of the environmental information and the position information.

[0368] The computer generates a relational expression between the position information and the range parameter for each environmental information. The generated relational expression is used as the parameter calculation formula.

[0369] ***Effects of Embodiment 4***

[0370] Sensor diagnosis device 100 can use the feature amount related to the position information of the object to determine the state of sensor group 200. As a result, sensor diagnosis device 100 can more accurately determine the state of sensor group 200.

[0371] The sensor diagnosis device 100 calculates the range parameter by calculating the parameter calculation formula, and calculates the normal range using the calculated range parameter. Thus, the sensor diagnosis device 100 can determine a more appropriate normal range. As a result, the sensor diagnosis device 100 can more accurately determine the state of the sensor group 200.

[0372] ***Example of Implementation Method 4***

[0373] Similar to the example of implementation mode 3, different range parameters may be used depending on the type of object.

[0374] Similar to the example of Embodiment 2, the state determination unit 150 may determine the degree of degradation of the sensor group 200 based on the ratio of the position feature amounts within the normal range or the ratio of the position feature amounts outside the normal range.

[0375] Similar to the example of the first embodiment, the state determination unit 150 may identify an abnormal sensor based on the state of each sensor set.

[0376] ***Supplementary implementation methods***

[0377] based on Figure 22 , describing the hardware structure of sensor diagnosis device 100.

[0378] Sensor diagnostic device 100 includes a processing circuit 109 .

[0379] The processing circuit 109 is hardware that realizes the data acquisition unit 110 , the object detection unit 120 , the environment determination unit 130 , the normal range determination unit 140 , and the state determination unit 150 .

[0380] The processing circuit 109 may be dedicated hardware, or may be the processor 101 that executes a program stored in the memory 102 .

[0381] When the processing circuit 109 is dedicated hardware, the processing circuit 109 is, for example, a single circuit, a complex circuit, a programmed processor, a parallel programmed processor, an ASIC, an FPGA, or a combination thereof.

[0382] ASIC is the abbreviation of Application Specific Integrated Circuit.

[0383] FPGA is short for Field Programmable Gate Array.

[0384] The sensor diagnostic device 100 may also have a plurality of processing circuits instead of the processing circuit 109. The plurality of processing circuits share the functions of the processing circuit 109.

[0385] In the sensor diagnostic device 100, part of the functions may be implemented by dedicated hardware, and the remaining functions may be implemented by software or firmware.

[0386] In this way, each function of the sensor diagnostic device 100 can be implemented by hardware, software, firmware, or a combination thereof.

[0387] The embodiments are illustrative examples of preferred modes and are not intended to limit the technical scope of the present invention. The embodiments may be partially implemented or implemented in combination with other modes. The steps described using flowcharts and the like may also be appropriately changed.

[0388] The "section" that is an element of the sensor diagnostic device 100 may also be replaced with "processing" or "step".

[0389] Reference Signs Explanation

[0390] 100: Sensor diagnostic device; 101: Processor; 102: Memory; 103: Auxiliary storage device; 104: Input / output interface; 109: Processing circuit; 110: Data acquisition section; 120: Object detection section; 130: Environment determination section; 140: Normal range determination section; 150: Status determination section; 190: Storage section; 191: Parameter database; 200: Sensor group; 201: Camera; 202: LIDAR; 203: Millimeter-wave radar; 204: Sonar.

Claims

1. A sensor diagnostic device, wherein, The sensor diagnostic device includes: a data acquisition unit that acquires a sensor data group from a sensor group including a plurality of sensors of different types; an object detection unit that calculates a position information group for an object existing around the sensor group based on the acquired sensor data group; an environment determination unit that determines the surrounding environment of the sensor group based on at least any one sensor data in the acquired sensor data group; a normal range determination unit that determines a normal range for the calculated position information group based on a parameter database and the determined environment, wherein the parameter database registers parameter data related to environment information and position information; and a state determination unit that determines the state of the sensor group based on the calculated position information group and the determined normal range, the parameter data is a parameter calculation formula representing a distribution related to the position information of the configuration obtained by using a sensor group that is normally used in a situation where a configuration is placed at a position identified by the position information in an environment identified by the environment information, the normal range determination unit selects an arbitrary sensor from the sensor group according to the determined environment, selects the position information corresponding to the selected sensor from the position information group, acquires the parameter calculation formula corresponding to the determined environment as the parameter data, calculates the acquired parameter calculation formula to calculate the range parameter corresponding to the selected position information, and uses the calculated range parameter to calculate the range of normal position information as the normal range.

2. The sensor diagnostic device according to claim 1, wherein the state determination unit determines whether each position information in the position information group is included in the normal range at each moment within a specified time, calculates the ratio of the position information outside the normal range within the specified time, and determines the state of the sensor group based on the calculated ratio.

3. The sensor diagnostic device according to claim 1, wherein the object detection unit calculates at least one position information in the position information group by using two or more sensor data acquired from two or more sensors.

4. The sensor diagnostic device according to claim 2, wherein the object detection unit calculates at least one position information in the position information group by using two or more sensor data acquired from two or more sensors.

5. The sensor diagnostic device according to any one of claims 1 to 4, wherein the environment determination unit selects two or more sensors from the sensor group and determines the environment by using two or more sensor data acquired from the selected two or more sensors.

6. A sensor diagnostic device, wherein, The sensor diagnostic device includes: a data acquisition unit that acquires a sensor data group from a sensor group including a plurality of sensors of different types; an object detection unit that calculates a position information group for an object existing around the sensor group based on the acquired sensor data group; an environment determination unit that determines the surrounding environment of the sensor group based on at least any one sensor data in the acquired sensor data group; A normal range determination unit that determines a normal range for the calculated position information group based on a parameter database and the determined environment, where the parameter database stores parameter data related to environment information and position information; and A state determination unit that determines the state of the sensor group based on the calculated position information group and the determined normal range, The parameter data is a parameter calculation formula representing a distribution related to the position information of the configured object obtained by using a sensor group that is normal when placed at the position identified by the position information in the environment identified by the environment information, The normal range determination unit selects an arbitrary sensor from the sensor group according to the determined environment, selects the position information corresponding to the selected sensor from the position information group, obtains the parameter calculation formula corresponding to the determined environment as the parameter data, calculates the obtained parameter calculation formula to calculate the range parameter corresponding to the selected position information, and uses the calculated range parameter to calculate the range of the normal position characteristic quantity as the normal range, The position characteristic quantity is a characteristic quantity of the position information.

7. The sensor diagnosis device according to claim 6, wherein, The state determination unit calculates the position characteristic quantity for each position information in the position information group at each moment within a specified time, determines whether each position characteristic quantity is included in the normal range at each moment within the specified time, calculates the ratio of the position characteristic quantities outside the normal range within the specified time, and determines the state of the sensor group based on the calculated ratio.

8. The sensor diagnosis device according to claim 6, wherein, The object detection unit calculates at least one position information in the position information group by using two or more sensor data obtained from two or more sensors.

9. The sensor diagnosis device according to claim 7, wherein, The object detection unit calculates at least one position information in the position information group by using two or more sensor data obtained from two or more sensors.

10. The sensor diagnosis device according to any one of claims 6 to 9, wherein, The environment determination unit selects two or more sensors from the sensor group and determines the environment by using two or more sensor data obtained from the selected two or more sensors.

11. A computer-readable recording medium having a sensor diagnostic program recorded thereon, wherein, This sensor diagnosis program causes a computer to execute the following processing: A data acquisition process of acquiring a sensor data group from a sensor group including multiple sensors of different types; An object detection process of calculating a position information group for an object existing around the sensor group based on the acquired sensor data group; An environment determination process of determining the surrounding environment of the sensor group based on at least any one of the sensor data in the acquired sensor data group; A normal range determination process of determining a normal range for the calculated position information group based on a parameter database and the determined environment, where the parameter database stores parameter data related to environment information and position information; And State determination process, which determines the state of the sensor group based on the calculated position information group and the determined normal range. The parameter data is a parameter calculation formula representing the distribution related to the position information of the configuration obtained by using a normal sensor group in a situation where a configuration is placed at the position identified by the position information in the environment identified by the environmental information. In the normal range determination step, an arbitrary sensor is selected from the sensor group according to the determined environment, the position information corresponding to the selected sensor is selected from the position information group, the parameter calculation formula corresponding to the determined environment is obtained as the parameter data, the obtained parameter calculation formula is calculated to calculate the range parameter corresponding to the selected position information, and the calculated range parameter is used to calculate the range of normal position information as the normal range.

12. A computer-readable recording medium storing a sensor diagnostic program, wherein, This sensor diagnosis program is used to cause a computer to execute the following processes: Data acquisition process, which acquires a sensor data group from a sensor group including a plurality of different types of sensors; Object detection process, which calculates a position information group for an object existing around the sensor group based on the acquired sensor data group; Environment determination process, which determines the surrounding environment of the sensor group based on at least any one of the sensor data in the acquired sensor data group; Normal range determination process, which determines the normal range for the calculated position information group based on the parameter database and the determined environment, where the parameter database registers parameter data related to environmental information and position information; And State determination process, which determines the state of the sensor group based on the calculated position information group and the determined normal range. The parameter data is a parameter calculation formula representing the distribution related to the position information of the configuration obtained by using a normal sensor group in a situation where a configuration is placed at the position identified by the position information in the environment identified by the environmental information. In the normal range determination step, an arbitrary sensor is selected from the sensor group according to the determined environment, the position information corresponding to the selected sensor is selected from the position information group, the parameter calculation formula corresponding to the determined environment is obtained as the parameter data, the obtained parameter calculation formula is calculated to calculate the range parameter corresponding to the selected position information, and the calculated range parameter is used to calculate the range of normal position feature quantities as the normal range. The position feature quantity is a feature quantity of the position information.

13. A sensor diagnostic device, wherein, This sensor diagnosis device includes: A data acquisition unit that acquires a sensor data group from a sensor group including a plurality of different types of sensors; An object detection unit that calculates a position information group for an object existing around the sensor group based on the acquired sensor data group; An environment determination unit that determines the surrounding environment of the sensor group based on at least any one of the sensor data in the acquired sensor data group; A normal range determination unit that determines the normal range for the calculated position information group according to the determined environment; and A state determination unit that determines the state of the sensor group based on the calculated position information group and the determined normal range. The normal range determination unit selects an arbitrary sensor from the sensor group according to the determined environment, selects the position information corresponding to the selected sensor from the position information group, obtains a parameter calculation formula corresponding to the determined environment, calculates the obtained parameter calculation formula to calculate the range parameter corresponding to the selected position information, and uses the calculated range parameter to calculate the range of normal position information as the normal range.

14. A sensor diagnostic device, wherein, This sensor diagnostic device includes: A data acquisition unit that acquires a sensor data group from a sensor group including a plurality of different types of sensors; An object detection unit that calculates a position information group for an object existing around the sensor group based on the acquired sensor data group; An environment determination unit that determines the environment around the sensor group based on at least any one of the sensor data in the acquired sensor data group; A normal range determination unit that determines a normal range for the calculated position information group according to the determined environment; and A state determination unit that determines the state of the sensor group based on the calculated position information group and the determined normal range. The normal range determination unit selects an arbitrary sensor from the sensor group according to the determined environment, selects the position information corresponding to the selected sensor from the position information group, obtains a parameter calculation formula corresponding to the determined environment, calculates the obtained parameter calculation formula to calculate the range parameter corresponding to the selected position information, and uses the calculated range parameter to calculate the range of normal position feature quantities as the normal range. The position feature quantity is a feature quantity of the position information.

Images