Blind spot detection system

Abstract

To provide a dead angle detection system that can prevent a work machine from continuing work in a situation where monitoring of the work machine is obstructed by a dead angle.SOLUTION: A dead angle detection system includes: monitoring area setting means for setting a monitoring area 71 around a work machine 20; a LiDAR3 for acquiring object presence information within the monitoring area 71; dead angle detection means for detecting a dead angle that is an area where the LiDAR3 cannot acquire object presence information within the region 71, based on the object presence information acquired by the LiDAR3; and countermeasure means for taking measures regarding the work machine 20 continuing work when the size of the dead angle detected by the dead angle detection means is equal to or larger than a threshold value.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to a blind spot detection system for detecting blind spots in a monitoring area.

Background Art

[0002] As disclosed in Patent Document 1, by monitoring the surroundings of a working machine, it is possible to detect an intrusion of an intruder or an abnormal operation of the working machine as an unsafe state. In Patent Document 1, in order to stably perform the determination process based on the distance, a distance calculation value representing the latest distance to the object is calculated based on a plurality of distance acquisition values in time series.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] By the way, when a blind spot occurs in the monitoring area and the size of this blind spot is so large as to hinder the monitoring of the working machine, it will hinder the detection of an unsafe state. If such a blind spot is left unattended, there is a risk that the work of the working machine will continue without being able to detect an unsafe state.

[0005] An object of the present invention is to provide a blind spot detection system capable of suppressing the working machine from continuing to work in a situation where the monitoring of the working machine is hindered by a blind spot.

Means for Solving the Problems

[0006] The present invention is characterized by comprising: a monitoring area setting means for setting a monitoring area around a work machine; an information acquisition device for acquiring information on the presence of objects within the monitoring area; a blind spot detection means for detecting a blind spot, which is an area within the monitoring area from which the information acquisition device cannot acquire information, based on the presence information acquired by the information acquisition device; and a countermeasure means for taking measures to prevent the work machine from continuing its work when the size of the blind spot detected by the blind spot detection means is greater than or equal to a threshold. [Effects of the Invention]

[0007] According to the present invention, measures are taken to prevent a work machine from continuing its work if the size of a blind spot within the monitoring area exceeds a threshold. For example, if the size of a blind spot within the monitoring area is large enough to hinder monitoring of the work machine, measures such as restricting the operation of the work machine or issuing a warning can be taken. By taking such measures, it is possible to prevent a work machine from continuing its work when monitoring of the work machine is obstructed by a blind spot. [Brief explanation of the drawing]

[0008] [Figure 1] This is a diagram illustrating the configuration of the blind spot detection system. [Figure 2] This is a side view of the work machine. [Figure 3] This diagram shows the circuit configuration of the blind spot detection system and the work machine. [Figure 4] This is a view of the surroundings of the work machine from above. [Figure 5] This diagram shows information about the presence of objects when the size of the blind spot within the monitoring area is within an acceptable range. [Figure 6] This diagram shows the current information regarding the existence of an object. [Figure 7] This is a diagram showing a 3D model of a work machine. [Figure 8] This figure shows point cloud data acquired by LiDAR. [Modes for carrying out the invention]

[0009] Hereinafter, preferred embodiments of the present invention will be described with reference to the drawings.

[0010] (Configuration of the blind spot detection system) The blind spot detection system according to an embodiment of the present invention detects blind spots within a monitoring area. As shown in Figure 1, a configuration diagram of the blind spot detection system 1, the blind spot detection system 1 includes a camera 2, a LiDAR 3, and an alarm device 7.

[0011] Camera 2 captures images of the work site. Multiple cameras 2 may be installed at the work site. Within the work site, a work machine 20 is performing work. This work machine 20 may be a work machine 20 with an operator on board, a work machine 20 that is remotely controlled, or a work machine 20 that is automatically driven.

[0012] LiDAR (Light Detection and Ranging or Laser Imaging Detection and Ranging) 3 acquires point cloud data indicating the distance from the location where the LiDAR 3 is mounted to objects (working machinery 20 or intruders) within the work site. Multiple LiDAR 3 units may be installed at the work site. Alternatively, a stereo camera or a TOF (Time Of Flight) sensor may be used instead of LiDAR 3.

[0013] The alarm device 7 is capable of issuing an alarm. Specifically, the alarm device 7 is equipped with a lamp and a speaker, and warns workers and others in the work area by illuminating the lamp or emitting a warning sound from the speaker.

[0014] (Configuration of the work machine) As shown in Figure 2, a side view of the work machine 20, the work machine 20 is a machine that performs work with an attachment 30, such as a hydraulic excavator. The work machine 20 has a machine body 25 equipped with a lower traveling body 21 and an upper rotating body 22, an attachment 30, and a cylinder 40.

[0015] The lower traveling body 21 is a part for driving the working machine 20 and, for example, includes crawlers. The upper revolving body 22 is rotatably attached to the upper part of the lower traveling body 21 via a slewing device 24. A cab (driver's cab) 23 is provided at the front part of the upper revolving body 22.

[0016] The attachment 30 is attached to the upper revolving body 22 so as to be rotatable in the vertical direction. The attachment 30 includes a boom 31, an arm 32, and a bucket 33. The boom 31 is attached to the upper revolving body 22 so as to be rotatable (able to raise and lower) in the vertical direction. The arm 32 is attached to the boom 31 so as to be rotatable in the vertical direction. The bucket 33 is attached to the arm 32 so as to be rotatable in the front-rear direction. The bucket 33 is a part for performing operations such as excavation, leveling, and scooping of earth and sand (the transported material). Note that the transported material held by the bucket 33 is not limited to earth and sand and may be stones or waste (such as industrial waste).

[0017] The cylinder 40 can rotate the attachment 30 hydraulically. The cylinder 40 is a hydraulic telescopic cylinder. The cylinder 40 includes a boom cylinder 41, an arm cylinder 42, and a bucket cylinder 43.

[0018] The boom cylinder 41 rotates the boom 31 with respect to the upper revolving body 22. The base end part of the boom cylinder 41 is rotatably attached to the upper revolving body 22. The tip end part of the boom cylinder 41 is rotatably attached to the boom 31.

[0019] The arm cylinder 42 rotates the arm 32 with respect to the boom 31. The base end part of the arm cylinder 42 is rotatably attached to the boom 31. The tip end part of the arm cylinder 42 is rotatably attached to the arm 32.

[0020] The bucket cylinder 43 rotates the bucket 33 relative to the arm 32. The base end of the bucket cylinder 43 is rotatably attached to the arm 32. The tip end of the bucket cylinder 43 is rotatably attached to a link member 34, which is rotatably attached to the bucket 33.

[0021] Furthermore, the work machine 20 has an angle sensor 52 and a tilt angle sensor 60.

[0022] The angle sensor 52 detects the rotation angle of the upper rotating body 22 relative to the lower traveling body 21. The angle sensor 52 is, for example, an encoder, resolver, or gyro sensor. In this embodiment, the rotation angle of the upper rotating body 22 is defined as 0° when the front of the upper rotating body 22 coincides with the front of the lower traveling body 21.

[0023] The tilt angle sensor 60 detects the posture of the attachment 30. The tilt angle sensor 60 comprises a boom tilt angle sensor 61, an arm tilt angle sensor 62, and a bucket tilt angle sensor 63.

[0024] The boom tilt angle sensor 61 is attached to the boom 31 and detects the attitude of the boom 31. The boom tilt angle sensor 61 is a sensor that acquires the tilt angle of the boom 31 with respect to the horizontal line, and is, for example, a tilt (acceleration) sensor. The boom tilt angle sensor 61 may also be a rotation angle sensor that detects the rotation angle of the boom foot pin (boom base) or a stroke sensor that detects the stroke amount of the boom cylinder 41.

[0025] The arm tilt angle sensor 62 is attached to the arm 32 and detects the posture of the arm 32. The arm tilt angle sensor 62 is a sensor that acquires the tilt angle of the arm 32 with respect to the horizontal line, and is, for example, a tilt (acceleration) sensor. The arm tilt angle sensor 62 may also be a rotation angle sensor that detects the rotation angle of the arm connecting pin (arm base end) or a stroke sensor that detects the stroke amount of the arm cylinder 42.

[0026] The bucket tilt angle sensor 63 is attached to the link member 34 and detects the attitude of the bucket 33. The bucket tilt angle sensor 63 is a sensor that acquires the tilt angle of the bucket 33 with respect to the horizontal line, and is, for example, a tilt (acceleration) sensor. The bucket tilt angle sensor 63 may also be a rotation angle sensor that detects the rotation angle of the bucket connecting pin (bucket base end) or a stroke sensor that detects the stroke amount of the bucket cylinder 43.

[0027] Furthermore, the work machine 20 is equipped with a GNSS sensor 26. The GNSS (Global Navigation Satellite System) sensor 26 is mounted on the upper rotating body 22 and detects the coordinates of the upper rotating body 22 within the work site. The GNSS sensor 26 is a positioning sensor and acquires the position of the work machine 20 (upper rotating body 22) in the global coordinate system. Note that instead of the GNSS sensor 26, a positioning sensor such as a GPS sensor or a distance measuring sensor such as a total station may be used.

[0028] (Blind spot detection system and circuit configuration of work machinery) As shown in Figure 3, which illustrates the circuit configuration of the blind spot detection system 1 and the work machine 20, the work machine 20 includes a work machine-side controller 81 and a work machine-side communication device 83.

[0029] The work machine controller 81 receives information regarding the slewing angle (attitude) of the upper slewing body 22 relative to the lower traveling body 21, as detected by the angle sensor 52. The work machine controller 81 also receives information regarding the attitude of the boom 31, as detected by the boom tilt angle sensor 61. The work machine controller 81 also receives information regarding the attitude of the arm 32, as detected by the arm tilt angle sensor 62. The work machine controller 81 also receives information regarding the attitude of the bucket 33, as detected by the bucket tilt angle sensor 63.

[0030] Furthermore, the controller 81 on the work machine side receives information about the position of the work machine 20, which has been acquired by the GNSS sensor 26.

[0031] The work machine-side controller 81 can control the operation of the attachment 30 and the slewing device 24. Specifically, the work machine-side controller 81 can restrict or stop the operation of the attachment 30 and the slewing device 24.

[0032] When the work machine 20 is operated automatically, the work machine controller 81 automatically controls the work machine 20. The work machine controller 81 controls the upper slewing body 22 and the attachment 30 so that they perform repetitive tasks. The work machine controller 81 automatically operates the slewing device 24 and the attachment 30 based on the detected values ​​of the angle sensor 52 and the tilt angle sensor 60. In this embodiment, the repetitive task is the task of excavating and removing soil.

[0033] The machine-side communication device 83 can communicate with the communication device 8 of the blind spot detection system 1, which will be described later.

[0034] The blind spot detection system 1 comprises a controller 5, a storage device 6, and a communication device 8. The communication device 8 can communicate with the work machine-side communication device 83 of the work machine 20.

[0035] The controller 5 includes an object detection unit 11, a position / attitude acquisition unit 12, a monitoring area setting unit 13, and a countermeasure unit 15.

[0036] The object detection unit 11 detects work machinery 20 within the work site based on images captured by the camera 2. The object detection unit 11 also detects intruders (people, dump trucks, etc.) within the work site based on images captured by the camera 2. Deep learning technology may be used to detect the work machinery 20 and intruders. The object detection unit 11 stores the detected intruders and other objects in the storage device 6.

[0037] The position and orientation acquisition unit 12 acquires the position of the work machine 20. The position of the work machine 20 is acquired by the GNSS sensor 26 and transmitted to the blind spot detection system 1.

[0038] Alternatively, the position of the work machine 20 may be obtained as follows. The position / orientation acquisition unit 12 uses the position (coordinates) of the global coordinate system to which the LiDAR 3 is attached and the distance from the LiDAR 3 to each point in the point cloud data to calculate the position (three-dimensional coordinate) of each point in the point cloud data in the global coordinate system. Next, the position / orientation acquisition unit 12 performs a perspective projection transformation on the three-dimensional coordinate of each point in the point cloud data to obtain the two-dimensional coordinate of each point in the point cloud data. Then, the position / orientation acquisition unit 12 superimposes the two-dimensional coordinate of each point in the point cloud data onto the two-dimensional image captured by the camera 2. Finally, the position / orientation acquisition unit 12 obtains the position of the work machine 20 in three dimensions from the three-dimensional coordinate of the point in the point cloud data that overlaps with the work machine 20 detected by the object detection unit 11.

[0039] Here, the global coordinate system positions of camera 2 and LiDAR 3 are obtained by positioning sensors such as GNSS sensors and distance measuring sensors such as total stations.

[0040] The monitoring area setting unit (monitoring area setting means) 13 sets a monitoring area around the work machine 20. As shown in Figure 1, the monitoring area 71 is an area centered on the position of the work machine 20 acquired by the position / orientation acquisition unit 12. In a plan view of the monitoring area 71 from above, the shape of the monitoring area 71 may be rectangular, circular, or elliptical.

[0041] As shown in Figure 4, which is a view of the area around the work machine 20 from above, the monitoring area 71 has a work area 72 and a peripheral area 73. The work area 72 is the area around the work machine 20 where the work machine 20 operates. The peripheral area 73 is set around the work area 72. The monitoring area setting unit 13 stores the monitoring area 71 in the storage device 6.

[0042] Here, the size of the work area 72 is widened or narrowed according to the operation phase of the work machine 20. For example, suppose the operation of the work area 72 consists of an operation phase of excavating soil from the soil pile 95 (excavation phase), an operation phase of rotating the upper slewing body 22 while holding the soil in the bucket 33 (lifting and slewing phase), an operation phase of discharging the soil onto the bed of the dump truck 90 (discharging phase), and an operation phase of rotating the upper slewing body 22 to above the soil pile 95 (returning and slewing phase). In this case, during the lifting and slewing phase and the return and slewing phase, the movement of the work machine 20 is larger compared to the excavation phase and the discharging phase, so the work area 72 is made larger accordingly. Conversely, during the excavation phase and the discharging phase, the movement of the work machine 20 is smaller compared to the lifting and slewing phase and the return and slewing phase, so the work area 72 is made smaller accordingly. In other words, the working area 72 is widened or narrowed according to the operation phase, so that the working area 72 does not become unnecessarily large.

[0043] The countermeasure unit 15 takes action to address an unsafe condition when it detects one. Here, an unsafe condition is defined as a state in which an intruder has entered the monitoring area 71 or a state in which the work machine 20 is malfunctioning. When an intruder has entered the monitoring area 71, the countermeasure unit 15 takes action as a countermeasure, which may be either a warning or a restriction on the operation of the work machine 20.

[0044] In this embodiment, the countermeasure unit 15 issues a warning when an intruder enters the surrounding area 73. Specifically, the lamp on the alarm device 7 lights up, and a warning sound is emitted from the speaker of the alarm device 7. On the other hand, the countermeasure unit 15 restricts the operation of the work machine 20 when an intruder enters the work area 72. Specifically, an operation restriction instruction is transmitted to the work machine 20 via the communication device 8. When the work machine side controller 81 of the work machine 20 receives the operation restriction instruction, it restricts or stops the operation of the attachment 30 and the swivel device 24.

[0045] Furthermore, the countermeasure unit 15 takes action if an operational abnormality occurs in the work machine 20. For example, if the four operation phases described above do not switch properly in an automatically operated work machine 20, it is determined that an operational abnormality has occurred in the work machine 20. When an operational abnormality occurs in the work machine 20, the countermeasure unit 15 issues a warning and restricts the operation of the work machine 20.

[0046] In the above configuration, as shown in Figure 1, if a dump truck 90 is positioned between camera 2 and the monitoring area 71, the dump truck 90 creates a blind spot A within the monitoring area 71. Additionally, a blind spot B is created behind the work machine 20 from the perspective of camera 2. If the size of these blind spots is large enough to interfere with monitoring the work machine 20, it will hinder the detection of unsafe conditions. Leaving such blind spots unaddressed could lead to the work of the work machine 20 continuing without detecting unsafe conditions.

[0047] Therefore, as shown in Figure 3, the controller 5 of the blind spot detection system 1 has a blind spot detection unit 17 and a threshold setting unit 18.

[0048] The LiDAR (information acquisition device) 3 acquires information about the presence of objects within the monitoring area 71 as point cloud data. The blind spot detection unit (blind spot detection means) 17 detects blind spots within the monitoring area 71 based on the information about the presence of objects acquired by the LiDAR 3. Here, a blind spot is an area within the monitoring area 71 where the LiDAR 3 cannot acquire information about the presence of objects.

[0049] Specifically, the blind spot detection unit 17 detects blind spots within the monitoring area 71 based on the object presence information acquired by LiDAR 3 when the size of the blind spot within the monitoring area 71 is within an acceptable range, and the object presence information acquired by LiDAR 3 at the current time. The blind spot detection unit 17 stores the detected blind spots in the storage device 6. Note that "the size of the blind spot is within an acceptable range" means that the size of the blind spot does not exceed a threshold described later.

[0050] First, the blind spot detection unit 17 instructs the LiDAR 3 to acquire information about the presence of an object when the size of the blind spot within the monitoring area 71 is within an acceptable range. Figure 5 shows the information about the presence of an object when the size of the blind spot within the monitoring area 71 is within an acceptable range. In Figure 5, a large amount of point cloud data has been acquired within the monitoring area 71, except for the blind spot B behind the work machine 20. Next, the blind spot detection unit 17 instructs the LiDAR 3 to acquire information about the presence of an object at the present time. Figure 6 shows the information about the presence of an object at the present time. In Figure 6, a large amount of point cloud data has been acquired within the monitoring area 71, except for the blind spot A caused by the dump truck 90 and the blind spot B behind the work machine 20.

[0051] As shown in Figure 6, if a blind spot A exists within the monitoring area 71 at this time, a difference will occur between the object presence information shown in Figure 5 and the object presence information shown in Figure 6. By comparing the two pieces of presence information, the blind spot A within the monitoring area 71 can be suitably detected.

[0052] Returning to Figure 3, the threshold setting unit (threshold setting means) 18 sets a threshold for the size of the blind spot. The threshold is set, for example, by numerical input. The threshold setting unit 18 stores the set threshold in the storage device 6.

[0053] The countermeasure unit (countermeasure means) 15 takes measures to prevent the work machine 20 from continuing its work when the size of the blind spot detected by the blind spot detection unit 17 is greater than or equal to a threshold. Specifically, the countermeasure unit 15 takes at least one of the following measures: a warning or a restriction on the operation of the work machine 20. If a warning is issued as a countermeasure, the worker who receives the warning can be alerted. If the operation of the work machine 20 is restricted as a countermeasure, the work machine 20 can be reliably prevented from continuing its work. This prevents the work machine 20 from continuing its work when its monitoring is obstructed by a blind spot.

[0054] Furthermore, the countermeasure unit 15 does not take any measures to prevent the work machine 20 from continuing its work if the size of the blind spot detected by the blind spot detection unit 17 is less than a threshold.

[0055] Here, the threshold setting unit 18 sets different thresholds for the work area 72 and the surrounding area 73. In this embodiment, the threshold set for the work area 72 is made smaller than the threshold set for the surrounding area 73. Here, in order to detect blind spots caused by people, the threshold set for the work area 72 is set based on the size of the person.

[0056] When a blind spot occurs in the work area 72, the degree to which the operator needs to pay attention to the continuation of the work machine 20 is higher than when a blind spot occurs in the surrounding area 73. Therefore, by setting the threshold value set for the work area 72 lower than the threshold value set for the surrounding area 73, countermeasures can be taken more easily when a blind spot occurs in the work area 72 than when a blind spot occurs in the surrounding area 73. As a result, the continuation of the work machine 20 can be more effectively suppressed when a blind spot occurs in the work area 72 than when a blind spot occurs in the surrounding area 73.

[0057] Furthermore, the countermeasures in the countermeasures unit 15 differ between the work area 72 and the surrounding area 73. In this embodiment, the countermeasure when a blind spot occurs in the work area 72 is to limit the operation of the work machine 20, and the countermeasure when a blind spot occurs in the surrounding area 73 is to issue a warning.

[0058] When a blind spot occurs in the work area 72, the degree to which the operator needs to pay attention to the continuation of the work machine 20 is higher than when a blind spot occurs in the surrounding area 73. Therefore, the countermeasure when a blind spot occurs in the work area 72 is to limit the operation of the work machine 20, and the countermeasure when a blind spot occurs in the surrounding area 73 is to issue a warning. This makes it possible to further discourage the continuation of the work machine 20 when a blind spot occurs in the work area 72 than when a blind spot occurs in the surrounding area 73.

[0059] However, the blind spot detection method described using Figures 5 and 6 cannot detect when part or all of the work machine 20 is in a blind spot.

[0060] As shown in Figure 3, the position and orientation acquisition unit (acquisition means) 12 acquires the position and orientation of the work machine 20. The position of the work machine 20 is acquired by the GNSS sensor 26. The orientation of the work machine 20 can be determined from the detected values ​​of the angle sensor 52 and the tilt angle sensor 60. The position and orientation acquisition unit 12 stores the position and orientation of the work machine 20 in the storage device 6. From the position and orientation of the work machine 20, the location where the work machine 20 is located can be estimated.

[0061] The blind spot detection unit 17 detects blind spots within the monitoring area 71 based on the position and orientation of the work machine 20 acquired by the position and orientation acquisition unit 12 and the presence information of objects acquired by the LiDAR 3.

[0062] Specifically, the blind spot detection unit 17 uses the position and orientation of the work machine 20 acquired by the position and orientation acquisition unit 12 to create a 3D model of the work machine 20. The 3D model of the work machine 20 is shown in Figure 7. Meanwhile, the blind spot detection unit 17 extracts point cloud data from the point cloud data acquired by LiDAR3 that overlap with the 3D model of the work machine 20 and clusters these points. The point cloud data acquired by LiDAR3 is shown in Figure 8.

[0063] The blind spot detection unit 17 superimposes a 3D model of the work machine 20 with clustered point cloud data. If clustered point cloud data is missing from the 3D model, the unit can determine that the portion of the work machine 20 with missing point cloud data is a blind spot. In this way, a part or all of the work machine 20 that is a blind spot can be effectively detected. The blind spot detection unit 17 stores the detected blind spots in the storage device 6.

[0064] The countermeasure unit 15 also takes countermeasures in the same manner if the size of the blind spot detected in this way exceeds a threshold.

[0065] In this embodiment, the presence information of objects within the monitoring area 71 is obtained in three dimensions from the point cloud data acquired by LiDAR3, and blind spots within the monitoring area 71 are detected. However, blind spots within the monitoring area 71 may also be detected by obtaining the presence information of objects within the monitoring area 71 in two dimensions using a camera 2 or the like.

[0066] (effect) As described above, according to the blind spot detection system 1 of this embodiment, if the size of the blind spot in the monitoring area 71 exceeds a threshold, measures are taken to prevent the work machine 20 from continuing its work. For example, if the size of the blind spot in the monitoring area 71 is large enough to hinder the monitoring of the work machine 20, measures such as restricting the operation of the work machine 20 or issuing a warning can be taken. By taking such measures, it is possible to prevent the work machine 20 from continuing its work when its monitoring is obstructed by a blind spot.

[0067] Furthermore, at least one of the following measures is taken: a warning or a restriction on the operation of the work machine 20. If a warning is issued as a countermeasure, the worker who receives the warning can be alerted. If the operation of the work machine 20 is restricted as a countermeasure, it is possible to reliably prevent the work machine 20 from continuing its work.

[0068] Furthermore, the thresholds differ between the work area 72 and the surrounding area 73. This allows for differences in the ease with which countermeasures can be taken between the work area 72 and the surrounding area 73. Here, if a blind spot occurs in the work area 72, the degree to which the worker needs to pay attention to the continuation of the work machine 20 is higher than if a blind spot occurs in the surrounding area 73. Therefore, for example, by making the threshold set for the work area 72 smaller than the threshold set for the surrounding area 73, countermeasures can be taken more easily if a blind spot occurs in the work area 72 than if a blind spot occurs in the surrounding area 73. In this case, the continuation of the work machine 20 can be more suppressed if a blind spot occurs in the work area 72 than if a blind spot occurs in the surrounding area 73.

[0069] Furthermore, the countermeasures differ between the work area 72 and the surrounding area 73. This allows for appropriate countermeasures to be implemented for each of the work area 72 and the surrounding area 73. Here, if a blind spot occurs in the work area 72, the degree to which the worker needs to pay attention to the continuation of the work machine 20 is higher than if a blind spot occurs in the surrounding area 73. Therefore, for example, the countermeasure when a blind spot occurs in the work area 72 is to limit the operation of the work machine 20, and the countermeasure when a blind spot occurs in the surrounding area 73 is to issue a warning. In this case, the continuation of the work machine 20 can be more suppressed when a blind spot occurs in the work area 72 than when a blind spot occurs in the surrounding area 73.

[0070] Furthermore, blind spots within the monitoring area 71 are detected based on the object presence information (point cloud data) acquired by LiDAR3 when the size of the blind spot within the monitoring area 71 is within an acceptable range, and the object presence information (point cloud data) acquired by LiDAR3 at the present time. If a blind spot exists within the monitoring area 71 at the present time, a difference will occur between the object presence information acquired when there is no blind spot and the object presence information acquired at the present time. By comparing the two sets of presence information, the blind spot within the monitoring area 71 can be suitably detected.

[0071] Furthermore, blind spots within the monitoring area 71 are detected based on the position and orientation of the work machine 20 and the object presence information (point cloud data) acquired by LiDAR 3. The location where the work machine 20 is located can be estimated from its position and orientation. If the object presence information acquired by LiDAR 3 is missing at the location where the work machine 20 is estimated to be located, it can be determined that the part of the work machine 20 where the presence information is missing is a blind spot. In this way, part or all of the work machine 20 that is in a blind spot can be suitably detected.

[0072] Although embodiments of the present invention have been described above, these are merely illustrative examples and do not particularly limit the present invention. Specific configurations and other aspects can be modified as appropriate. Furthermore, the actions and effects described in the embodiments of the invention are merely a list of the most preferred actions and effects resulting from the present invention, and the actions and effects according to the present invention are not limited to those described in the embodiments. [Explanation of Symbols]

[0073] 1. Blind Spot Detection System 2 cameras 3 LiDAR (information acquisition device) 5 Controllers 6 Storage device 7 Alarm device 8. Communication equipment 11 Object detection unit 12 Position / attitude acquisition unit (acquisition means) 13 Monitoring area setting section (monitoring area setting means) 15 Countermeasures Department (Measures to Countermeasure) 17. Blind Spot Detection Unit (Blind Spot Detection Means) 18. Threshold setting unit (threshold setting means) 20 Working Machines 21 Lower running body 22 Upper rotating body 23 Cab 24 Swivel device 25 Machine body 26 GNSS sensors 30 Attachments 31 Boom 32 Arms 33 buckets 34 Link members 40 cylinders 41 Boom Cylinder 42 Arm Cylinder 43 Bucket Cylinder 52 Angle Sensor 60 Tilt Angle Sensor 61 Boom tilt angle sensor 62 Arm tilt angle sensor 63 Bucket tilt angle sensor 71 Monitoring area 72 Work area 73 Peripheral area 81. Work machine side controller 83 Communication device on the work machine side 90 Dump truck 95 Sand and debris mound

Claims

1. A monitoring area setting means for setting a monitoring area around a work machine, An information acquisition device that acquires information about the existence of objects within the aforementioned monitoring area, A blind spot detection means for detecting a blind spot, which is an area within the monitoring area where the information acquisition device cannot acquire the existence information, based on the existence information acquired by the information acquisition device, If the size of the blind spot detected by the blind spot detection means exceeds a threshold, the countermeasure means provides for taking measures to prevent the work machine from continuing its operation. A threshold setting means for setting the aforementioned threshold, It has, The blind spot detection means detects the difference between the existence information previously acquired by the information acquisition device and the existence information acquired by the information acquisition device at the present time, when the size of the blind spot within the monitoring area is within an acceptable range, as the blind spot that has occurred in the monitoring area at the present time. The monitoring area comprises a work area set around the work machine and a peripheral area set around the work area. The monitoring area setting means widens or narrows the size of the work area according to a plurality of operation phases that constitute a series of repetitive operations performed by the work machine. The threshold setting means is characterized by making the threshold different for the work area and the surrounding area, in a blind spot detection system.

2. A monitoring area setting means for setting a monitoring area around a work machine, An information acquisition device that acquires information about the existence of objects within the aforementioned monitoring area, A blind spot detection means for detecting a blind spot, which is an area within the monitoring area where the information acquisition device cannot acquire the existence information, based on the existence information acquired by the information acquisition device, If the size of the blind spot detected by the blind spot detection means exceeds a threshold, the countermeasure means provides for taking measures to prevent the work machine from continuing its operation. An acquisition means for acquiring the position and orientation of the aforementioned work machine, A threshold setting means for setting the aforementioned threshold, It has, The blind spot detection means estimates the location where the work machine is located using the position and orientation of the work machine acquired by the acquisition means, and detects the portion where the presence information is missing at the location where the work machine is estimated to be located as the blind spot within the monitoring area. The monitoring area comprises a work area set around the work machine and a peripheral area set around the work area. The monitoring area setting means widens or narrows the size of the work area according to a plurality of operation phases that constitute a series of repetitive operations performed by the work machine. The threshold setting means is characterized by making the threshold different for the work area and the surrounding area, in a blind spot detection system.

3. The blind spot detection system according to claim 1 or 2, characterized in that the countermeasure means includes at least one of warning and limiting the operation of the work machine as the countermeasure.

4. The blind spot detection system according to any one of claims 1 to 3, characterized in that the countermeasures are different for the work area and the surrounding area.

Images