WO2016194426A1

WO2016194426A1 - Work machine for mine

Info

Publication number: WO2016194426A1
Application number: PCT/JP2016/056713
Authority: WO
Inventors: 佑介日永田; 拓久哉中; 信一魚津
Original assignee: 日立建機株式会社
Priority date: 2015-06-02
Filing date: 2016-03-04
Publication date: 2016-12-08
Also published as: JP6523050B2; JP2016223963A

Abstract

The purpose of the present invention is to detect and correct the axial deviation (positional deviation) of a plurality of different types of sensors and make accurate obstacle detection possible in a case where obstacle detection is carried out through the combination of the plurality of sensors. A calibration device according to the present invention is provided with: a positional deviation determination permission unit 114 for determining, on the basis of a geometric shape measured by a first measurement device 11, whether an obstacle is suitable for detecting the positional deviation between the first measurement device 11 and a second measurement device 12; and an intersensor calibration unit 117 for detecting the amount of positional deviation between the first measurement device 11 and the second measurement device 12 on the basis of the position detected by the first measurement device 11 for an obstacle determined by the positional deviation determination permission unit 114 to be suitable for detecting the positional deviation and the position detected by the second measurement device 12 for the obstacle.

Description

Mining work machine

The present invention relates to an obstacle detection device suitable for use in a mining work vehicle such as an off-road dump truck.

Generally, in mines, mining work machines such as excavators and dump trucks are used for mining and transporting earth and sand. Mining work machines used in mines are required to be unmanned from the viewpoint of safety and cost reduction. In dump trucks, since the amount of earth and sand transported per unit time is directly linked to the progress of mining, efficient operation is required. Therefore, in order to efficiently transport a large amount of earth and sand outside the mining site, a mining system using an autonomously traveling dump truck capable of continuous operation is required.

However, the mining roads that run dump trucks are off-road and there are many bad roads, so there are concerns about collisions with obstacles such as dirt walls and other vehicles when driving dump trucks autonomously and driving unattended. The If an obstacle occurs on the traveling road and an autonomous traveling unmanned dump truck comes into contact with the obstacle and stops, the operation of the mine is stopped for a long time.
Therefore, in order to improve the reliability of the autonomously traveling dump truck, it is possible to detect obstacles on the front vehicle and the road at an early stage, and to perform follow-up traveling following the preceding vehicle and avoiding obstacles. A reliable obstacle detection system is needed.

Conventionally, as this kind of obstacle detection system, an obstacle detection device such as a millimeter wave radar, a laser sensor, a camera or a stereo camera has been used. The millimeter wave radar has a high environmental resistance capable of operating even when dust or rain occurs, and has a high measurement distance performance. On the other hand, since a stereo camera or a laser sensor can measure a three-dimensional shape, an obstacle on the road can be detected with high accuracy. There is also a method of improving the obstacle detection performance by combining these sensors.

To use multiple sensors of different types, it is necessary to accurately grasp the relative position of each sensor. In particular, when attaching to a mine dump truck, the vehicle body is large, so it is necessary to consider misalignment due to aging in addition to calibration at the time of attachment. For example, Japanese Patent Application Laid-Open No. 2010-249613 (Patent Document 1) discloses an obstacle recognition device that corrects the axial misalignment between an in-vehicle camera and an in-vehicle radar caused by aging based on positional information of an obstacle detected by each sensor. It has been published. Specifically, the obstacle recognition device of Patent Literature 1 is an obstacle recognition device that recognizes an obstacle by combining a plurality of sensor information, and the front camera that acquires first parameter information about the obstacle, Based on the millimeter wave radar that acquires the second parameter information about the obstacle, and the first parameter information and the second parameter information, the azimuth misalignment amount of the front camera or the millimeter wave radar is calculated, and the calculated misalignment A correction unit that corrects the axial deviation of the front camera or the millimeter wave radar based on the amount and a storage unit that stores the axial deviation amount are provided (see summary).

JP 2010-249613 A

The obstacle detection device of Patent Document 1 is intended for vehicles traveling on general roads. Millimeter-wave radar has low lateral position resolution due to the characteristics of the sensor, and the lateral position error tends to be large when detecting the center position of a large vehicle such as a mine dump truck or a specially shaped vehicle such as an excavator. There is. When the axis misalignment between the camera and the millimeter wave radar is corrected by the above method based on the detection result having a large error, there is a possibility that the obstacle detection accuracy is worse than before the correction.

The present invention has been made in view of the above problems. In the case where obstacle detection is performed by combining a plurality of different types of sensors, axial misalignment (position displacement) of the plurality of sensors is detected and corrected. The purpose is to enable easy obstacle detection.

In order to achieve the above object, a calibration device of the present invention includes a first measurement device capable of measuring a geometric shape in a measurement region and a second measurement device capable of detecting the position of an obstacle. A calibration device that is provided in an obstacle detection device that detects an obstacle existing around a vehicle and corrects a positional deviation between the first measurement device and the second measurement device;
An obstacle recognition unit capable of detecting at least one of the height, width, shape, image feature, or type of an obstacle present in the measurement area based on information measured by the first measurement device; ,
Position shift determination permission for determining whether the obstacle is an obstacle suitable for detecting a position shift between the first measurement device and the second measurement device based on information detected by the obstacle recognition unit. And
A detection position by the first measurement device for an obstacle determined to be an obstacle suitable for detecting a displacement by the position deviation determination permission unit, and a detection position by the second measurement device for the obstacle; And a sensor-to-sensor calibration unit that detects the amount of positional deviation between the first measurement device and the second measurement device.

In the calibration apparatus according to the present invention, the correction of the relative position change between the sensors caused by the secular change or the like can be automatically performed from the selection of the obstacle suitable for performing the calibration to the correction. Thereby, the healthy state of the obstacle detection device can be maintained.

Issues, configurations, and effects other than those described above will be clarified by the following description of the embodiments.

It is the block diagram which showed the outline | summary of the structure which concerns on the Example of the calibration apparatus of this invention. It is the conceptual diagram shown about dispersion | distribution of the obstruction detection position by the size of a target. It is a flowchart figure which shows the operation | movement procedure which concerns on the Example of the calibration apparatus of this invention. It is the conceptual diagram explaining the problem which arises at the time of position shift between sensors. It is the conceptual diagram explaining the problem which arises at the time of position shift between sensors. It is the conceptual diagram explaining the method to determine whether it is the same with respect to the obstruction which the 1st measuring device and the 2nd measuring device measured. It is the conceptual diagram explaining the method to determine whether it is the same with respect to the obstruction which the 1st measuring device and the 2nd measuring device measured. It is the conceptual diagram explaining the parameter | index of position shift determination. It is a flowchart figure which shows the operation | movement procedure which determines the position shift with a 2nd measuring device and a 2nd measuring device. It is a flowchart figure which shows the operation | movement procedure which determines the presence or absence of execution of the calibration between sensors.

FIG. 1 is a block diagram showing an outline of a configuration according to an embodiment of a calibration apparatus of the present invention.

The vehicle 1 includes an obstacle detection device 200. The obstacle detection device 200 detects an obstacle present around the vehicle 1. The obstacle detection device 200 includes a first measurement device 11 and a second measurement device 12 in front of the vehicle body (front side) as a plurality of sensors. The first measuring device is a sensor capable of measuring the shape of an obstacle such as a monocular camera, a stereo camera, a LIDAR, or a TOF sensor. That is, the first measuring device 11 is a sensor capable of measuring a geometric shape in the measurement region. The second measuring device 12 is a sensor that can measure the position of an obstacle such as a millimeter wave sensor. In the present embodiment, the first measuring device 11 and the second measuring device 12 are attached to the front of the vehicle, but a part of the measurement area measured by the first measuring device 11 and the second measuring device 12, or If all are superposed, the present invention can be carried out regardless of the installation positions of the first measuring device 11 and the second measuring device 12.

In this embodiment, a mine dump truck used in a mine is described as the vehicle 1. The vehicle 1 may be a vehicle other than a mining dump truck used in a mine. Mining work trucks including mining dump trucks and vehicles other than mining dump trucks are called mining work machines. Moreover, the calibration apparatus 130 of this invention is applicable also to vehicles other than the working machine for mines.

First, the selection of an obstacle to be subjected to the positional deviation determination using the first measuring device 11 will be described.

In order to select an obstacle, the calibration device 130 is provided with a determination permission unit 131. The determination permission unit 131 includes a first obstacle detection unit 112, an obstacle recognition unit 113, and a positional deviation determination permission unit 114. The determination permission unit 131 configures an obstacle selection unit that selects a target obstacle for performing a positional deviation determination. Hereinafter, an obstacle for performing misalignment determination or an object suitable for misalignment determination is referred to as a target obstacle.

Note that the calibration device 130 is a device that corrects misalignment between the first measurement device 11 and the second measurement device 12, and in FIG. 1, the calibration device 130, the first measurement device 11, and the second measurement device 12. And are configured separately. However, the first measuring device 11 and the second measuring device 12 may be included in the calibration device 130.

The first measurement device 11 performs measurement in the measurement region, and the first obstacle detection unit 112 detects the position of the obstacle based on the information. Further, the obstacle recognizing unit 113 recognizes the information on the obstacle measured by the first obstacle detecting unit 112 based on the information of the first measuring device 11 and the first obstacle detecting unit 112. The obstacle information recognized at this time is at least one of the height, width, shape, image feature, and type of the obstacle.

FIG. 2 is a conceptual diagram showing dispersion of obstacle detection positions depending on the size of the target.
FIG. 2 shows how the vehicle 1 measures a large target 21 and a small target 22.

The target (large size) 21 exists in the measurement area 31. At this time, the position measured by the second measuring means is estimated to be some part of the target (large size) 21 existing in the measurement region. For this reason, in the case of the large target 21, the dispersion | distribution tends to become large compared with the case where the target is a target (small) 22 such as a general passenger car. In this embodiment, the displacement of the installation positions of the first measurement device 11 and the second measurement device 22 is determined based on the position information of the same obstacle detected by the first obstacle detection unit 112 and the second obstacle detection unit 122. Assumes that For this reason, it can be said that the target (small) 22 having a small dispersion of obstacle detection positions is more suitable for determining the displacement between the sensors than the target (large) 21 having a large dispersion of obstacle detection positions.

The displacement determination permission unit 114 determines the displacement of the first measurement device 11 and the second measurement device 12 based on the height, width, shape, image feature, and type of the obstacle detected by the obstacle recognition unit 113. It is determined whether it is suitable to do. For example, the range of the height and width of the obstacle is set in advance, and if it is within the range, it is determined that the obstacle is suitable for the obstacle for determining the displacement.

Alternatively, the information in the obstacle database unit 118 may be used to determine whether or not the object is suitable for an obstacle for determining positional deviation. The obstacle database unit 118 is configured by a storage device that registers in advance information on obstacles suitable for determining positional deviation between sensors. The obstacle database unit 118 may store the height and width ranges of the obstacle for determining the target obstacle.

When any one of the detected obstacle's height, width, shape, image feature, type, or a plurality of items match (when the condition is met), the misregistration determination permission unit 114 moves the obstacle between the sensors. It is determined that it is suitable for the determination of misalignment. That is, the positional deviation determination permission unit 114 selects the obstacle as a target obstacle.

Hereinafter, description will be made using the algorithm flow of FIG. FIG. 3 is a flowchart showing an operation procedure according to the embodiment of the calibration apparatus of the present invention.

The power is turned on to the first measuring device 11 and the computer 13, and the measurement of the obstacle is started (step S1). The first measurement device 11 sends the shape information in the measurement area to the first obstacle detection unit 112 (step S2). The first obstacle detection unit 112 determines the position of the obstacle based on the shape information from the first measurement device 11 (step S3). Next, based on the shape information in the measurement region measured by the first measurement device 11 and the position information of the obstacle detected by the first obstacle detection unit 112, the obstacle recognition unit 113 uses the height, width, and shape of the obstacle. Any one or more of image features and types is detected (step S4). The positional deviation determination permission unit 114 is the first when any one or more of the height, width, shape, image feature, and type of the obstacle detected by the obstacle recognition unit 113 satisfies a preset condition. It is determined that there is an obstacle (target obstacle) suitable for detecting the positional deviation between the measurement device 11 and the second measurement device 12, and the positional deviation determination is permitted (step S5). When the position deviation determination is permitted in step S5, the process proceeds to step 7 (step S6). If the position deviation determination is not permitted in step S5, the process returns to step S1 (step S6). In step S7, the presence / absence of the target obstacle and position information are presented to the system (step S7). As a presentation method at this time, there is a method of presenting such information on the display 125 (see FIG. 1), and a method of passing the presence / absence of an obstacle and position information suitable for detecting misalignment to another processing unit. .

Next, a method for detecting misalignment between the first measuring device 11 and the second measuring device 12 will be described with reference to FIGS.

As shown in FIG. 1, a determination unit 132 is provided in the calibration device 130 in order to detect a positional deviation between the first measurement device 11 and the second measurement device 12. The determination unit 132 includes a second obstacle detection unit 122 and a positional deviation determination unit 115. The calibration device 130 uses the second measurement device 12, the second obstacle detection unit 122, and the displacement determination unit 115 to detect a displacement between the first measurement device 11 and the second measurement device 12. The detected misregistration information is reported by the misregistration reporting unit 116.

The determination permission unit 131, the determination unit 132, and an inter-sensor calibration unit 117 described later constitute a calibration device 130.

FIG. 4 shows a measurement result when the first measurement device 11 and the second measurement device 12 are not displaced from the initial setting position. FIG. 4 is a conceptual diagram illustrating a problem that occurs when the position of the sensor is displaced. It can be seen that the obstacle position detected by the first measuring device 11 and the obstacle position detected by the second measuring device 12 overlap.

Next, FIG. 5 shows a case where the installation positions of the first measurement device 11 and the second measurement device 12 are deviated from the initial setting positions. FIG. 5 is a conceptual diagram illustrating a problem that occurs when the position of the sensor is displaced. In this example, the second measuring device 12 is shifted from the first measuring device 11 by an angle of −θ in the yaw direction. For this reason, the sensor coordinate system of the second measuring device 12 is shifted from the sensor coordinate system of the first measuring device 11 by θ in the yaw direction. As a result, the same target should be measured, but the positions of the obstacles are not overlapped as shown in FIG. In this case, since there is a possibility that one obstacle may be erroneously recognized as there are a plurality of obstacles, it is necessary to detect the state of deviation between the sensors.

As shown in FIG. 1, the second obstacle detection unit 122 detects an obstacle based on information in the measurement area measured by the second measurement device 12 capable of detecting the position of the obstacle. When the displacement determination permission unit 114 determines that there is an obstacle suitable for the obstacle displacement determination based on the information measured by the first measuring device 11, the same obstacle as the obstacle suitable for the determination is determined. The obstacle is detected from the obstacles detected by the second obstacle detector 122. As a search method for the same obstacle, the fact that the amount of displacement does not increase in the vicinity is used even when a displacement between sensors occurs.

The search method for the same obstacle will be described with reference to FIGS. 6 and 7 are conceptual diagrams illustrating a method for determining whether or not an obstacle measured by the first measurement device and the second measurement device is the same.

As shown in FIG. 6, at time t, there is an obstacle in the area for determining the correspondence of the obstacle set in advance, and the obstacle position detected by the first measuring device 11 and the second measuring device 12 The detected obstacle position overlaps. At this time, it is determined that the two obstacles are the same obstacle. Further, at the subsequent times t + 1, t + 2,..., T + n, as long as the first measuring device 11 and the second measuring device 12 can follow the obstacles, the obstacles are regarded as the same obstacle, The positional information is stored in the positional deviation determination unit 115.

For this purpose, the misalignment determination unit 115 detects the first obstacle detection information accumulation unit 115a and the second obstacle detection unit 122 that accumulate time-series information of the obstacle detected by the first obstacle detection unit 112. A second obstacle detection information storage unit 115b for storing obstacle time-series information.

On the other hand, at the times t−1, 1-2,..., Tn before the determination that the obstacle is the same, the obstacle position detected by the first measurement device 11 and the detection by the second measurement device 12 are the same. The obstacle position is stored in the misalignment determination unit 115 as obstacle information of the same obstacle (FIG. 7). If it is determined from the information on the same obstacle detected by the first measurement device 11 and the second measurement device 12 stored in the displacement determination unit 115 that the displacement has occurred, the displacement determination unit reports the displacement. It reports to the unit 116 how much the installation position of the first measurement device 11 and the installation position of the second measurement device 12 are shifted.

A method for determining misalignment will be described with reference to FIG. FIG. 8 is a conceptual diagram illustrating an index for determining misalignment.

For example, as shown in FIG. 8, the position of the obstacle detected at the same time among the obstacles detected by the first obstacle detector 112 and the second obstacle detector 122 as shown in FIG. A pair of information is designated as measurement 1, measurement 2, and measurement 3. The distance of the obstacle position of each pair at this time is measured. When the maximum value of the distance exceeds a set threshold value, or when the cumulative value exceeds a set threshold value, it is determined that the first measurement device 11 and the second measurement device 12 are misaligned.

Referring to FIG. 9, the algorithm flow for determining misalignment will be described. FIG. 9 is a flowchart illustrating an operation procedure for determining a positional deviation between the second measurement device and the second measurement device.

Steps 1 to 7 are the same as described in FIG. The second measuring device 12 measures the measurement area (step S8). Based on the information, the second obstacle detection unit 122 detects the presence and position of an obstacle (step S9). When the system receives a position deviation determination permission report in step S7, position deviation determination is performed (step S10). First, in the displacement determination unit 115, the first obstacle detection unit 112 detects in Step S3, and the second obstacle detection unit 122 detects an obstacle determined to be suitable for the displacement determination in Step S5. Search from obstacles. If there is a corresponding obstacle, a misalignment determination is performed (step S10). When it is determined that there is a positional shift, the process proceeds from step S11 to step S12. If there is no displacement, the process proceeds to step S1. Further, in the case where the obstacle detected by the second obstacle detection unit 122 in step S10 is not the same obstacle as the obstacle determined to be suitable for the positional deviation determination in step S5, The process proceeds to step S1. When the position shift determination unit 115 determines that there is a position shift, the position shift report unit 116 (see FIG. 1) reports that the installation positions of the first measurement device 11 and the second measurement device 12 are shifted from the initial setting positions. To do. As a presentation method at this time, there are a method of presenting such information on the display 125, and a method of passing positional deviation information to another processing unit.

In FIG. 1, the misalignment reporting unit 116 is provided separately from the calibration device (calibration unit) 130. However, the misalignment report unit 116 may be provided inside the calibration device 130.

Next, calibration between sensors will be described. FIG. 10 is a flowchart illustrating an operation procedure for determining whether or not calibration between sensors is performed.

When the positional deviation reporting unit 116 reports that the installation positions of the first measuring device 11 and the second measuring device 12 are deviated from the initial positions, the inter-sensor calibration unit 117 can cope with the deviation by program parameter correction. It is determined whether or not. If it is determined that it can be handled, the calibration between the first measuring device 11 and the second measuring device 12 is performed, and how much parameter correction should be performed is calculated. When it is determined that the response is not possible, the functions of the first measurement device 11 and the second measurement device 12 are stopped, and the user is notified that a large displacement between the sensors has occurred.

For example, as shown in FIG. 8, among the obstacles detected by the first obstacle detection unit 112 and the second obstacle detection unit 122 as shown in FIG. A pair of position information of the detected obstacle is defined as measurement 1, measurement 2, and measurement 3. The distance between obstacles in each pair at this time is measured. When the maximum value of the distance exceeds a set threshold value, or when the cumulative value exceeds a set threshold value, it is determined that the first measurement device 11 and the second measurement device 12 are misaligned.

In the calibration, for example, a relative position parameter that minimizes the sum of squares of the distances between obstacles in each pair is searched. There is a method of setting a new inter-sensor position that has the smallest sum of squares of distances between obstacles in the search. The parameter search method includes the steepest gradient method, the least square method, the Newton method, the Levenberg Marquardt method, and the like.

Specific description will be made based on the algorithm flow of FIG. Prior to step S12, the steps described in FIG. 9 are executed.

When there is a report of the positional deviation between the first measuring device 11 and the second measuring device 12 in step S12, it is determined whether the positional deviation can be corrected (step S13). This determination is made based on the evaluation value calculated in step S10 in FIG. If the conditions set in advance are satisfied, it is determined that the parameter correction of the positional deviation is possible, and the process proceeds to step S16. If the condition cannot be satisfied, the process proceeds to step S14.

When the process proceeds to step S14, the user is informed that the misalignment between the first measuring device 11 and the second measuring device 12 cannot be corrected (step S14). As a presentation method, presentation by a buzzer sound or presentation on the display 125 can be considered. Then, in order to prevent malfunction, the function of an external field sensor (the 1st measuring device 11, the 2nd measuring device 12) is stopped automatically (Step S15).

In step S16, automatic calibration is performed to determine the current relative position of the first measurement device 11 and the second measurement device 12. Based on the obtained relative position, the positional deviation generated in the first measuring device 11 and the second measuring device 12 is corrected.

This correction is performed as follows in the case of FIG. In FIG. 7, it is determined at time t that the obstacle detected by the first measuring device 11 and the obstacle detected by the second measuring device 12 are the same obstacle. At this time t, a positional shift that has occurred in the first measuring device 11 and the second measuring device 12 from the relative position between the obstacle detected by the first measuring device 11 and the obstacle detected by the second measuring device 12. It is difficult to detect accurately.

Therefore, the positional deviation generated in the first measuring device 11 and the second measuring device 12 is detected by going back in time. For example, for obstacles determined as the same obstacle, the obstacles detected by the first measuring device 11 and the obstacles detected by the second measuring device 12 are traced back to the time t-1 or the time t-2. The relative positional relationship with the object is obtained by calculation.

At time t-1 or time t-2, there is a large difference between the position of the obstacle detected by the first measuring device 11 and the position of the obstacle detected by the second measuring device 12. The retroactive time may be a time before time t-2. The difference between the position of the obstacle detected by the first measuring device 11 and the position of the obstacle detected by the second measuring device 12 usually increases as the time goes back. Then, based on the obtained relative positional relationship between the two obstacles, it is possible to accurately detect the positional deviation that has occurred in the first measuring device 11 and the second measuring device 12.

Alternatively, in the case of FIG. 6, it is known that the same obstacle is detected by the first measuring device 11 and the second measuring device 12 at the present time (time t). Therefore, when a difference occurs between the position of the obstacle detected by the first measuring device 11 and the position of the obstacle detected by the second measuring device 12 at future times t + 1, t + 2,. In addition, based on this difference, a positional shift generated in the first measuring device 11 and the second measuring device 12 may be detected.

According to the present embodiment, the correction of the relative position change between the sensors caused by the secular change or the like can be automatically performed from the selection of the obstacle suitable for performing the calibration to the correction. Thereby, the healthy state of the obstacle detection device can be maintained. In particular, since a dump truck for mining travels off-road, it is not known when a positional shift between sensors occurs.
Therefore, automatic calibration from obstacle selection to correction leads to an improvement in the operating rate of the vehicle.

Also, dump trucks for mines are often assembled locally (mine). By applying this embodiment, the obstacle detection apparatus can be easily and accurately calibrated in the dump truck assembled on site.

In addition, this invention is not limited to each above-mentioned Example, Various modifications are included. For example, the above-described embodiments have been described in detail for easy understanding of the present invention, and are not necessarily limited to those having all the configurations. Further, a part of the configuration of one embodiment can be replaced with the configuration of another embodiment, and the configuration of another embodiment can be added to the configuration of one embodiment. Further, it is possible to add, delete, and replace other configurations for a part of the configuration of each embodiment.

In addition, each of the above-described configurations, functions, processing units, processing means, and the like may be realized by hardware by designing a part or all of them with, for example, an integrated circuit. Each of the above-described configurations, functions, and the like may be realized by software by interpreting and executing a program that realizes each function by the processor. Information such as programs, tables, and files that realize each function can be stored in a memory, a hard disk, a recording device such as an SSD (Solid State Drive), or a recording medium such as an IC card, an SD card, or a DVD.

Also, the control lines and information lines indicate what is considered necessary for the explanation, and not all the control lines and information lines on the product are necessarily shown. Actually, it may be considered that almost all the components are connected to each other.

DESCRIPTION OF SYMBOLS 1 ... Vehicle (work machine for mines), 11 ... 1st measuring device, 12 ... 2nd measuring device, 112 ... 1st obstacle detection part, 113 ... Obstacle recognition part, 114 ... Misalignment determination permission part, 115 ... Misregistration determination unit 116 ... Misregistration report unit, 117 ... Inter-sensor calibration unit, 118 ... Obstacle database unit, 122 ... Second obstacle detection unit, 130 ... Calibration device, 131 ... Determination permission unit, 132 ... Determination unit, 200... Obstacle detection device.

Claims

Obstacle detection device for detecting an obstacle existing around a vehicle, having a first measurement device capable of measuring a geometric shape in a measurement region and a second measurement device capable of detecting the position of the obstacle Provided in the calibration device for correcting the positional deviation of the first measurement device and the second measurement device,
An obstacle recognition unit capable of detecting at least one of the height, width, shape, image feature, or type of an obstacle present in the measurement area based on information measured by the first measurement device; ,
Position shift determination permission for determining whether the obstacle is an obstacle suitable for detecting a position shift between the first measurement device and the second measurement device based on information detected by the obstacle recognition unit. And
A detection position by the first measurement device for an obstacle determined to be an obstacle suitable for detecting a displacement by the position deviation determination permission unit, and a detection position by the second measurement device for the obstacle; A calibration apparatus comprising: an inter-sensor calibration unit that detects a positional deviation amount between the first measurement apparatus and the second measurement apparatus based on the above.
The calibration device according to claim 1,
The misalignment determination permitting unit detects misalignment between the first measurement device and the second measurement device when the height and width of the obstacle are within a predetermined threshold range. A calibration apparatus characterized by determining an obstacle suitable for determination.
The calibration device according to claim 1,
As an obstacle information suitable for misalignment determination in the misalignment determination permission unit, it has an obstacle database unit that holds any information of height, width, shape, image characteristic or type of an obstacle,
The positional deviation determination permitting unit matches the obstacle measured by the first measuring device in any of the height, width, shape, image feature, or type of the obstacle held in the obstacle database unit. A calibration apparatus, wherein when determined, the obstacle is determined to be an obstacle suitable for determining a positional deviation between the first measurement device and the second measurement device.
The calibration device according to claim 1,
A first obstacle detection unit that measures the position of an obstacle in a measurement region based on information measured by the first measurement device;
A second obstacle detection unit that measures the position of the obstacle in the measurement region based on the information measured by the second measurement device;
When the displacement determination permission unit determines that the obstacle is an obstacle suitable for determining displacement between the first measurement device and the second measurement device, the first obstacle detection unit Whether there is a deviation in the installation positions of the first measurement device and the second measurement device based on the detected location information of the obstacle and the location information of the obstacle detected by the second obstacle detection unit. A position deviation determination unit for determining
A calibration apparatus, comprising: a positional deviation report unit that reports the presence / absence of a deviation in installation position between the first measurement apparatus and the second measurement apparatus.
The calibration device according to claim 4,
The inter-sensor calibration unit detects the first obstacle detection unit when the positional deviation report unit reports that the installation position of the first measurement device and the second measurement device is shifted. A positional deviation between the first measurement device and the second measurement device is corrected based on the obstacle information of the obstacle and the obstacle information of the obstacle detected by the second obstacle detection unit. A calibration device.
The calibration device according to claim 4,
The displacement determination unit includes a first obstacle detection information accumulation unit that accumulates time series information of obstacles detected by the first obstacle detection unit and a time series of obstacles detected by the second obstacle detection unit. A second obstacle detection information storage unit for storing information;
The displacement determination unit is configured such that the obstacle position detected by the first obstacle detection unit and the obstacle position detected by the second obstacle detection unit approach within a preset distance in the same time zone. The obstacle detected by the first obstacle detection unit and the obstacle detected by the second obstacle detection unit are determined to be the same obstacle, and the obstacle detected by the first measurement device A calibration device that detects a displacement amount between the first measurement device and the second measurement device based on the position information of the obstacle and the position information of the obstacle detected by the second measurement device.
The calibration device according to claim 6,
The misregistration determination unit detects a misregistration amount by determining whether the obstacle detected by the first obstacle detection unit and the obstacle detected by the second obstacle detection unit are the same. A calibration apparatus characterized in that the calibration is performed based on information on the obstacle accumulated in the first obstacle detection information accumulation unit and the second obstacle detection information accumulation unit at a time point retroactive from the time point.
In a mining work machine that runs in a mine,
A mine work machine comprising the calibration device according to claim 1.