Construction machine, information processing device, and program

Abstract

The invention provides a technology capable of enabling a construction machine to execute a more appropriate operation. A shovel (100) according to one embodiment of the present disclosure is provided with a work object state prediction unit (302B) and an operation planning unit (302C). The work object state prediction unit (302B) predicts, on the basis of the trajectory of the bucket (6) on the basis of the operation being executed by the shovel (100) or the next operation to be executed, the state of the sand of the work object after the completion of the operation being executed by the shovel (100) or the next operation to be executed. Furthermore, the operation planning unit (302C) determines, from among the plurality of operations, the next operation of the operation being executed by the shovel (100) or the next operation of the next operation to be executed, on the basis of the prediction result of the state of the sand of the future work object predicted by the work object state prediction unit (302B).

Description

Technical Field

[0001] The present disclosure relates to a construction machine and the like. Background Art

[0002] Conventionally, construction machines such as excavators are known (see Patent Document 1).

[0003] Prior Art Literature

[0004] Patent Literature

[0005] Patent Document 1: Japanese Patent Application Publication No. 2021-188432 Summary of the invention

[0006] Technical issues to be solved by the invention

[0007] For example, from the viewpoint of work efficiency, it is preferable for the construction machine to perform more appropriate operations according to various conditions.

[0008] Therefore, an object of the present invention is to provide a technology that enables a construction machine to perform more appropriate operations.

[0009] Means for solving technical problems

[0010] In order to achieve the above object, in one embodiment of the present disclosure,

[0011] Provided is a construction machine comprising:

[0012] The motion planning unit determines a future motion of the construction machine from among a plurality of motions based on the execution status of the motion of the construction machine.

[0013] Furthermore, in another embodiment of the present disclosure,

[0014] An information processing device is provided, comprising:

[0015] The motion planning unit determines a future motion of the construction machine from among a plurality of motions based on the execution status of the motion of the construction machine.

[0016] Furthermore, in yet another embodiment of the present disclosure,

[0017] A program is provided for causing an information processing device to execute the following steps:

[0018] The action planning step determines the future action of the construction machine from a plurality of actions based on the execution status of the action of the construction machine.

[0019] Furthermore, in yet another embodiment of the present disclosure,

[0020] A program is provided that causes a support device to perform the following steps:

[0021] an action planning step of determining a future action of the construction machine from a plurality of actions according to the execution status of the action of the construction machine; and

[0022] A notification step of notifying an operator of the construction machine of the action determined in the action planning step.

[0023] Effect of the Invention: According to the above-described embodiment, the construction machine can perform more appropriate operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 This is a diagram showing an example of a work support system.

[0025] Figure 2 It is a top view showing an example of a shovel.

[0026] Figure 3 This is a diagram showing an example of a configuration related to remote control of a shovel.

[0027] Figure 4 This is a diagram showing an example of the hardware configuration of a shovel.

[0028] Figure 5 This is a diagram showing an example of the hardware configuration of an information processing device.

[0029] Figure 6 This is a functional block diagram showing a first example of the functional configuration of the work support system.

[0030] Figure 7 This is a diagram for explaining an example of the relationship between the timing of processing related to the operation plan of the shovel and the operation of the plan target.

[0031] Figure 8 This is a diagram for explaining another example of the relationship between the timing of processing related to the operation plan of the shovel and the operation of the plan target.

[0032] Fig. 9 This is a state change diagram showing an example of changes in the operation of the shovel during slope construction work.

[0033] Fig.10 This is a state change diagram showing an example of changes in the operation of the shovel during the leveling work.

[0034] Fig.11 This is a functional block diagram showing a second example of the functional structure of the work support system.

[0035] Fig.12 This is a flowchart schematically showing an example of processing related to the start of the autonomous operation of the shovel.

[0036] Fig.13This is a main flowchart schematically showing an example of processing related to the motion plan of the shovel and the generation of the bucket trajectory.

[0037] Fig.14 This is a diagram showing an example of an observation target area.

[0038] Fig.15 This is a sub-routine diagram schematically showing an example of processing related to the generation of the bucket trajectory.

[0039] Fig.16 This is a diagram showing an example of cost conditions and operation parameters corresponding to a plurality of operation sections of the excavation operation of the shovel.

[0040] Fig.17 This is a flowchart schematically showing an example of processing related to the motion control of the shovel. DETAILED DESCRIPTION

[0041] Hereinafter, embodiments will be described with reference to the drawings.

[0042] [Overview of Operation Support System]

[0043] refer to Figure 1 to Figure 3 The outline of the operation support system SYS according to the present embodiment will be described.

[0044] Figure 1 FIG. 1 is a diagram showing an example of the operation support system SYS. Figure 1 A left side view of the excavator 100 is shown in FIG. Figure 2 It is a plan view showing an example of the shovel 100 . Figure 3 1 is a diagram showing an example of a structure related to the remote control of the shovel 100. In the following, the direction in which the attachment AT extends when the shovel 100 is viewed from above ( Figure 2 The upper direction of the excavator 100 is defined as “front”, and the direction in the excavator 100 or the direction viewed from the excavator 100 is described.

[0045] like Figure 1 As shown, the operation support system SYS includes a shovel 100 , an information processing device 200 , and a sensor group 300 .

[0046] The operation support system SYS cooperates with the shovel 100 using the information processing device 200 , and performs support related to the operation of the shovel 100 .

[0047] The shovel 100 included in the operation support system SYS may be one or a plurality of shovels.

[0048] In the operation support system SYS, the shovel 100 is a construction machine that is a target of support related to operation.

[0049] like Figure 1 , Figure 2 As shown, the shovel 100 includes a lower traveling body 1 , an upper swing body 3 , an attachment AT including a boom 4 , an arm 5 , and a bucket 6 , and a cab 10 .

[0050] The lower traveling body 1 uses crawler tracks 1C to make the excavator 100 travel. The crawler tracks 1C include a left crawler track 1CL and a right crawler track 1CR. The crawler tracks 1CL are hydraulically driven by a traveling hydraulic motor 1ML. Similarly, the crawler tracks 1CL are hydraulically driven by a traveling hydraulic motor 1MR. Thus, the lower traveling body 1 can travel by itself.

[0051] The upper revolving body 3 is mounted on the lower traveling body 1 so as to be revolvable (freely revolvable) via the revolving mechanism 2. For example, the upper revolving body 3 is revolved relative to the lower traveling body 1 by hydraulically driving the revolving mechanism 2 with a revolving hydraulic motor 2M.

[0052] The boom 4 is mounted at the front center of the upper revolving body 3 so as to be able to pitch about a rotation axis in the left-right direction. The arm 5 is mounted at the front end of the boom 4 so as to be able to rotate about a rotation axis in the left-right direction. The bucket 6 is mounted at the front end of the arm 5 so as to be able to rotate about a rotation axis in the left-right direction.

[0053] The bucket 6 is an example of an end attachment, and is used for excavation work, slope work, or leveling work, for example.

[0054] The bucket 6 is mounted on the front end of the arm 5 in a manner that can be appropriately replaced according to the work content of the excavator 100. That is, a bucket different from the bucket 6, such as a relatively large bucket, a bucket for slope, a bucket for dredging, etc., can be mounted on the front end of the arm 5 instead of the bucket 6. In addition, a terminal attachment of a type other than a bucket, such as a mixer, a crusher, a pulverizer, etc., can also be mounted on the front end of the arm 5. In addition, a preliminary attachment such as a quick coupling, a tilt rotator, etc. can also be provided between the arm 5 and the terminal attachment.

[0055] The boom 4, the arm 5 and the bucket 6 are hydraulically driven by a boom cylinder 7, an arm cylinder 8 and a bucket cylinder 9, respectively.

[0056] The cab 10 is a control room in which an operator rides to operate the shovel 100. The cab 10 is mounted on the front left side of the upper swing body 3, for example.

[0057] The shovel 100 is equipped with a communication device 60 and can communicate with the information processing device 200 via a predetermined communication line NW.

[0058] The communication line NW includes, for example, a local area network (LAN) at the construction site. Furthermore, the communication line NW may also include a wide area network (WAN). The wide area network includes, for example, a mobile communication network with a base station as a terminal, a satellite communication network using a communication satellite, the Internet, etc. Furthermore, the communication line NW may also include, for example, a short-distance communication line based on a wireless communication standard such as WiFi or Bluetooth (registered trademark).

[0059] For example, the shovel 100 operates driven elements such as the lower traveling body 1 (ie, a pair of left and right crawler tracks 1CL and 1CR), the upper swing body 3, the boom 4, the arm 5, and the bucket 6 according to operations performed by an operator riding in the cab 10.

[0060] Furthermore, the shovel 100 may be configured to be remotely operated (remotely operated) from the outside of the shovel 100 instead of being operable by an operator riding in the cab 10, or, in addition to being operable by an operator riding in the cab 10, to be remotely operated from the outside of the shovel 100. When the shovel 100 is remotely operated, the interior of the cab 10 may be unmanned. Furthermore, when the shovel 100 is dedicated to remote operation, the cab 10 may be omitted. The following description is based on the premise that the operator's operation includes at least one of the operation of the operating device 26 by the operator in the cab 10 and the remote operation by an external operator.

[0061] For example, Figure 3 As shown, the remote operation includes operating the shovel 100 by inputting operation related to the actuator of the shovel 100 by the remote operation support device 400, and the remote operation support device 400 can communicate with the shovel 100 through the communication line NW. The remote operation support device 400 can be provided separately from the information processing device 200, or it can be the information processing device 200.

[0062] The remote operation support device 400 is, for example, installed in a management center that externally manages the operation of the shovel 100. Furthermore, the remote operation support device 400 may be a portable operation terminal, in which case the operator can remotely operate the shovel 100 while directly checking the operation status of the shovel 100 from the vicinity of the shovel 100.

[0063] The shovel 100 can transmit an image showing the surrounding conditions including the front of the shovel 100 (hereinafter referred to as a "surrounding image") based on the camera image output by the camera device mounted on the shovel 100 to the remote operation support device 400, for example, through the communication device 60 described later. Furthermore, the shovel 100 can transmit the camera image output by the camera device to the remote operation support device 400 through the communication device 60, and the remote operation support device 400 processes the camera image received from the shovel 100 and generates the surrounding image. Then, the remote operation support device 400 can display the surrounding image showing the surrounding conditions including the front of the shovel 100 on its own display device. In addition, similarly, various information images (information screens) displayed on the output device 50 (display device) inside the cab 10 of the shovel 100 can also be displayed on the display device of the remote operation support device 400. Thus, the operator using the remote operation support device 400 can remotely operate the shovel 100 while checking the display contents such as an image or information screen showing the conditions around the shovel 100 displayed on the display device. In addition, the shovel 100 can operate the actuators to drive the driven elements such as the lower traveling body 1, the upper swing body 3, the boom 4, the arm 5 and the bucket 6 according to the remote operation signal indicating the contents of the remote operation received from the remote operation support device 400 by the communication device 60.

[0064] Furthermore, the remote operation may include, for example, a method of operating the shovel 100 based on external voice input or gesture input to the shovel 100 by a person (e.g., a worker) around the shovel 100. Specifically, the shovel 100 recognizes voices made by workers around the shovel 100 or gestures made by workers through a voice input device (e.g., a microphone) or a gesture input device (e.g., a camera) mounted on the shovel 100. Then, the shovel 100 can operate the actuator according to the content of the recognized voice or gesture, thereby driving the driven elements such as the lower traveling body 1 (left and right crawlers 1C), the upper swing body 3, the boom 4, the arm 5, and the bucket 6.

[0065] Furthermore, the excavator 100 can also automatically operate the actuator regardless of the operation content of the operator. Thus, the excavator 100 can realize the function of automatically operating at least a part of the driven elements such as the lower traveling body 1, the upper swing body 3, and the attachment AT, that is, the so-called "automatic operation function" or "machine control (MC) function".

[0066] The automatic operation function includes, for example, a semi-automatic operation function (operation support type MC function). The semi-automatic operation function is a function that automatically operates a driven element (actuator) other than the driven element (actuator) of the operation object according to the operation of the operator. In addition, the automatic operation function may include a fully automatic operation function (fully automatic type MC function). The fully automatic operation function is a function that automatically operates at least a part of a plurality of driven elements (hydraulic actuators) without the operation of the operator. In the excavator 100, when the fully automatic operation function is effective, the interior of the cab 10 may be unmanned. In addition, when the excavator 100 is dedicated to fully automatic operation, the cab 10 may be omitted. In addition, the semi-automatic operation function or the fully automatic operation function, for example, include a rule-based automatic operation function. The rule-based automatic operation function is an automatic operation function in the following manner: the action content of the driven element (actuator) of the automatic operation object is automatically determined according to a predetermined rule. In addition, the semi-automatic operation function or the fully automatic operation function, etc. may also include an autonomous operation function. The autonomous operation function is an automatic operation function in which the shovel 100 autonomously performs various judgments and determines the operation contents of the driven elements (hydraulic actuators) to be automatically operated based on the judgment results.

[0067] Furthermore, the operation of the excavator 100 can also be monitored remotely. In this case, a remote monitoring support device having the same function as the remote operation support device 400 can be provided. The remote monitoring support device is, for example, the information processing device 200. Thus, a monitor who is a user of the remote monitoring support device can monitor the operation status of the excavator 100 while confirming the peripheral image displayed on the display device of the remote monitoring support device. Furthermore, for example, when it is determined to be necessary from the perspective of safety, the monitor can intervene in the operation or automatic operation of the excavator 100 by the operator by using the input device of the remote monitoring support device to make a predetermined input, thereby making the excavator 100 stop in an emergency.

[0068] The information processing device 200 communicates with the shovel 100 to cooperate with each other and provide support related to the operation of the shovel 100 .

[0069] The information processing device 200 is, for example, a server device or a management terminal device, such as a management office set up in the construction site of the excavator 100 or a management center located at a location different from the construction site of the excavator 100 for managing the operating status of the excavator 100. The server device can be a local server or a cloud server, or it can be an edge server. The management terminal device can be, for example, a fixed terminal device such as a desktop PC (Personal Computer), or a portable terminal device (mobile terminal) such as a tablet terminal, a smart phone, or a laptop PC. In the latter case, workers at the construction site, supervisors who supervise the work, managers who manage the construction site, etc. can carry the portable information processing device 200 and move around the construction site. And, in the latter case, the operator can, for example, bring the portable information processing device 200 into the cab of the excavator 100.

[0070] The information processing device 200 acquires data related to the operating state from the shovel 100, for example. Thus, the information processing device 200 can grasp the operating state of the shovel 100 and monitor whether the shovel 100 has abnormalities or the like. Furthermore, the information processing device 200 can display data related to the operating state of the shovel 100 through the display device 208 described later, for example, and allow the user to confirm. Furthermore, the information processing device 200 can, for example, cause the learning model to learn the operating state of the shovel 100 and generate a learned model for supporting the operation of the shovel 100.

[0071] The information processing device 200 can also transmit various data such as programs and reference data used in the processing of the controller 30 and the like in the shovel 100 to the shovel 100. Thus, the shovel 100 can perform various processes related to the operation of the shovel 100 using various data downloaded from the information processing device 200.

[0072] The sensor group 300 is installed at the construction site of the shovel 100. The working object is, for example, sand and soil in the construction area around the shovel 100.

[0073] For example, when the operation support system SYS includes a plurality of shovels 100 , the sensor group 300 is provided for each shovel 100 . When the plurality of shovels 100 included in the operation support system SYS work at the same construction site, one sensor group 300 may be commonly used for the plurality of shovels 100 .

[0074] The sensor group 300 includes sensors 300-1 to 300-M (M: an integer greater than or equal to 2). The sensors 300-1 to 300-M measure the state of objects at the construction site around the excavator 100 and obtain measurement data related to the state. The objects at the construction site include, in addition to the work objects (sand and soil in the construction area) around the excavator 100, other construction machinery such as excavators and bulldozers around the excavator 100, or construction vehicles such as trucks for transporting sand and soil. The state of an object includes the shape or characteristics of the object.

[0075] Sensors 300-1 to 300-M include, for example, ranging sensors (distance sensors). Range finding sensors include, for example, LIDAR (Light Detecting and Ranging), millimeter wave radar, ultrasonic sensor, infrared sensor, etc. Furthermore, sensors 300-1 to 300-M may include, for example, 3D cameras such as stereo cameras and TOF (Time Of Flight) cameras that can acquire data related to distance (depth) in addition to two-dimensional images. Furthermore, in sensors 300-1 to 300-M, ranging sensors and 3D cameras are mixed together. Thus, the sensor group 300 can acquire measurement data representing the shape of objects at the construction site around the excavator 100. Hereinafter, for the sake of convenience, sensors such as ranging sensors or 3D cameras that can acquire measurement data representing the shape of an object are sometimes referred to as "shape sensors."

[0076] Furthermore, the sensors 300-1 to 300-M may include a multi-wavelength spectroscopic camera. The multi-wavelength spectroscopic camera includes, for example, a multi-spectral camera or a hyperspectral camera. Thus, for example, the sensor group 300 can obtain measurement data representing the characteristics of objects at the construction site around the excavator 100, such as the hardness or water content of sand. Hereinafter, for convenience, a sensor such as a multi-wavelength spectroscopic camera that can obtain measurement data representing the characteristics of an object is sometimes referred to as a "characteristic sensor."

[0077] For example, the sensors 300-1 to 300-M include a plurality of shape sensors. Furthermore, the plurality of shape sensors may be disposed at different positions of the construction site around the excavator 100, and the sensing range of each may overlap with the sensing range of at least one other shape sensor. Thus, for example, in the measurement data of a shape sensor, even if the measurement data representing the shape of an object in a part of the sensing range cannot be obtained due to occlusion, the measurement data representing the shape of the object in the range may be obtained from other shape sensors. Therefore, the sensor group 300 may more reliably obtain the measurement data representing the shape of the object at the construction site around the excavator 100.

[0078] Furthermore, the sensors 300-1 to 300-M may include a plurality of characteristic sensors. Furthermore, the plurality of characteristic sensors may be disposed at different locations of the construction site around the excavator 100, and the sensing range of each may overlap with at least one other characteristic sensor. Thus, for example, in the measurement data of a characteristic sensor, even if the measurement data representing the characteristics of an object in a part of the sensing range cannot be obtained due to occlusion, the measurement data representing the characteristics of the object in the range may be obtained from other shape sensors. Therefore, the sensor group 300 may more reliably obtain the measurement data representing the characteristics of the objects in the construction site around the excavator 100.

[0079] Furthermore, the sensors 300-1 to 300-M may include sensors having the functions of a shape sensor and a characteristic sensor (hereinafter referred to as "comprehensive sensors"). In this case, the sensors 300-1 to 300-M may include a plurality of comprehensive sensors. Furthermore, the plurality of characteristic sensors may be disposed at different locations of the construction site around the excavator 100, and the sensing range of each may overlap with at least one other characteristic sensor.

[0080] The sensor group 300 may simply include only one shape sensor or one characteristic sensor. Also, the operation support system SYS may simply include only one sensor capable of acquiring measurement data related to the state of an object at the construction site around the shovel 100 instead of the sensor group 300 .

[0081] The sensors 300-1 to 300-M may be fixed to the construction site around the shovel 100, or may be mounted on a movable object that can move in the construction site around the shovel 100. The movable object includes, for example, a construction machine or a construction vehicle that moves in the construction site. Furthermore, the movable object that can move in the construction site may include, for example, an aerial object such as a drone that flies over the construction site.

[0082] The outputs (measured data) of the sensors 300-1 to 300-M are input to the information processing device 200 through the communication line NW. The outputs of the sensors 300-1 to 300-M are directly input to the information processing device 200 through the communication line NW, for example. Furthermore, the outputs of the sensors 300-1 to 300-M may be temporarily input to the shovel 100 through the communication line NW, and then input to the information processing device 200 via the shovel 100. Furthermore, when the sensors 300-1 to 300-M are mounted on a predetermined device such as the above-mentioned mobile body, the outputs of the sensors 300-1 to 300-M may be temporarily input to the inside of the predetermined device, and then input to the information processing device 200 from the device.

[0083] [Hardware structure of the operation support system]

[0084] Then, except Figure 1 to Figure 3 In addition, refer to Figure 4 , Figure 5 The hardware configuration of the operation support system SYS will be described.

[0085] In addition, the hardware configuration of the remote operation support device 400 may be the same as that of the information processing device 200. Therefore, illustration and description of the hardware configuration of the remote operation support device 400 are omitted.

[0086] <Hardware structure of excavator>

[0087] Figure 4 This is a block diagram showing an example of the hardware configuration of the shovel 100 .

[0088] In addition, Figure 4 In the figure, a double line indicates a path for transmitting mechanical power, a solid line indicates a path for high-pressure working oil to drive a hydraulic actuator, a dashed line indicates a path for transmitting pilot pressure, and a dotted line indicates a path for transmitting electrical signals.

[0089] The excavator 100 includes various components such as a hydraulic drive system related to the hydraulic drive of the driven elements, an operating system related to the operation of the driven elements, a user interface system related to information exchange with the user, a communication system related to communication with the outside, and a control system related to various controls.

[0090] Hydraulic drive system

[0091] like Figure 4 As shown, as described above, the hydraulic drive system of the excavator 100 includes a hydraulic actuator HA, which hydraulically drives the driven elements such as the lower traveling body 1 (left and right crawler tracks 1C), the upper swing body 3, the boom 4, the arm 5 and the bucket 6. In addition, the hydraulic drive system of the excavator 100 involved in this embodiment includes an engine 11, a regulator 13, a main pump 14 and a control valve 17.

[0092] The hydraulic actuator HA includes travel hydraulic motors 1ML and 1MR, a swing hydraulic motor 2M, a boom cylinder 7, an arm cylinder 8, a bucket cylinder 9, and the like.

[0093] In addition, the shovel 100 may replace part or all of the hydraulic actuator HA with an electric actuator. That is, the shovel 100 may be a hybrid shovel or an electric shovel.

[0094] The engine 11 is a prime mover of the excavator 100 and a main power source in the hydraulic drive system. The engine 11 is, for example, a diesel engine that uses diesel as fuel. The engine 11 is, for example, mounted on the rear of the upper slewing body 3. The engine 11 is, for example, directly or indirectly controlled by a controller 30 described later and rotates at a constant speed set in advance to drive the main pump 14 and the pilot pump 15.

[0095] In addition, other prime movers (for example, electric motors) or the like may be mounted on the shovel 100 instead of the engine 11 , or other prime movers or the like may be mounted on the shovel 100 in addition to the engine 11 .

[0096] The regulator 13 controls (adjusts) the discharge amount of the main pump 14 under the control of the controller 30. For example, the regulator 13 adjusts the angle of the swash plate of the main pump 14 (hereinafter referred to as "tilt angle") according to a control command from the controller 30.

[0097] The main pump 14 supplies hydraulic oil to the control valve 17 through a high-pressure hydraulic line. The main pump 14 is mounted, for example, at the rear of the upper slewing body 3, similarly to the engine 11. As described above, the main pump 14 is driven by the engine 11. The main pump 14 is, for example, a variable displacement hydraulic pump, and as described above, under the control of the controller 30, the piston stroke length is adjusted by adjusting the deflection angle of the swash plate by the regulator 13, thereby controlling the discharge flow rate or discharge pressure.

[0098] The control valve 17 drives the hydraulic actuator HA according to the operation of the operating device 26 by the operator, the content of the remote operation, or the operation instruction corresponding to the automatic operation function. The control valve 17 is mounted, for example, on the central part of the upper slewing body 3. As described above, the control valve 17 is connected to the main pump 14 via a high-pressure hydraulic pipeline, and the working oil supplied from the main pump 14 is selectively supplied to each hydraulic actuator according to the operation of the operator or the operation instruction corresponding to the automatic operation function. Specifically, the control valve 17 includes a plurality of control valves (reversing valves) that control the flow rate and flow direction of the working oil supplied from the main pump 14 to each hydraulic actuator HA.

[0099] "operating system"

[0100] like Figure 4 As shown, the operating system of the excavator 100 includes a pilot pump 15 , an operating device 26 , a hydraulic control valve 31 , a shuttle valve 32 , and a hydraulic control valve 33 .

[0101] The pilot pump 15 supplies pilot pressure to various hydraulic devices via the pilot line 25. Like the engine 11, the pilot pump 15 is mounted, for example, at the rear of the upper swing body 3. The pilot pump 15 is, for example, a fixed displacement hydraulic pump and is driven by the engine 11 as described above.

[0102] In addition, the pilot pump 15 may be omitted. In this case, various hydraulic devices may be supplied with relatively low-pressure hydraulic oil after the relatively high-pressure hydraulic oil discharged from the main pump 14 is reduced in pressure by a predetermined pressure reducing valve as a pilot pressure.

[0103] The operating device 26 is provided near the operator's seat of the cab 10, and is used by the operator to operate various driven elements. Specifically, the operating device 26 is used by the operator to operate the hydraulic actuator HA that drives each driven element, and as a result, the operator can operate the driven element that is the drive target of the hydraulic actuator HA. The operating device 26 includes a pedal device or a lever device for operating each driven element (hydraulic actuator HA).

[0104] For example, Figure 4 As shown, the operating device 26 is a hydraulic pilot type. Specifically, the operating device 26 uses the working oil supplied from the pilot pump 15 through the pilot line 25 and the pilot line 25A branched from it to output the pilot pressure corresponding to the operation content to the pilot line 27A on the secondary side. The pilot line 27A is connected to one of the inlet ports of the reciprocating valve 32, and is connected to the control valve 17 via the pilot line 27 connected to the discharge port of the reciprocating valve 32. As a result, the pilot pressure corresponding to the operation content related to various driven elements (hydraulic actuator HA) in the operating device 26 can be input to the control valve 17 via the reciprocating valve 32. Therefore, the control valve 17 can drive each hydraulic actuator HA according to the operation content of the operating device 26 by the operator or the like.

[0105] Furthermore, the operating device 26 may also be an electric type. In this case, the pilot line 27A, the reciprocating valve 32, and the hydraulic control valve 33 are omitted. Specifically, the operating device 26 outputs an electrical signal corresponding to the operation content (hereinafter referred to as "operation signal"), and the operation signal is input to the controller 30. Furthermore, the controller 30 outputs a control instruction corresponding to the content of the operation signal to the hydraulic control valve 31, that is, a control signal corresponding to the operation content of the operating device 26. As a result, a pilot pressure corresponding to the operation content of the operating device 26 is input from the hydraulic control valve 31 to the control valve 17, and the control valve 17 can drive each hydraulic actuator HA according to the operation content of the operating device 26.

[0106] Furthermore, the control valve (direction change valve) built into the control valve 17 for driving each hydraulic actuator HA may be an electromagnetic solenoid type. In this case, the operation signal output from the operation device 26 may be directly input to the control valve 17 (ie, the electromagnetic solenoid type control valve).

[0107] Furthermore, as described above, a part or all of the hydraulic actuator HA may be replaced with an electric actuator. In this case, the controller 30 may output a control command corresponding to the operation content of the operating device 26 or the content of the remote operation specified by the remote operation signal to the electric actuator or a driver driving the electric actuator. Furthermore, when the shovel 100 is remotely operated, the operating device 26 may be omitted.

[0108] The hydraulic control valve 31 is provided for each driven element (hydraulic actuator HA) of each operation object of the operating device 26, and is provided for each driving direction of the driven element (hydraulic actuator HA) (for example, the lifting direction and the lowering direction of the boom 4). For example, two hydraulic control valves 31 are provided for each double-acting hydraulic actuator HA for driving the lower traveling body 1, the upper swing body 3, the boom 4, the dipper arm 5 and the bucket 6. The hydraulic control valve 31 can be provided, for example, in the pilot line 25B between the pilot pump 15 and the control valve 17, and is configured to be able to change its flow area (that is, the cross-sectional area through which the working oil can flow). Thus, the hydraulic control valve 31 can output a specified pilot pressure to the pilot line 27B on the secondary side using the working oil of the pilot pump 15 supplied through the pilot line 25B. Therefore, the hydraulic control valve 31 can indirectly act on the control valve 17 via the shuttle valve 32 between the pilot line 27B and the pilot line 27, thereby allowing a predetermined pilot pressure corresponding to a control signal from the controller 30 to act on the control valve 17. Therefore, for example, the controller 30 can supply a pilot pressure corresponding to an operation command corresponding to the automatic operation function from the hydraulic control valve 31 to the control valve 17, thereby realizing the operation of the shovel 100 based on the automatic operation function.

[0109] Furthermore, the controller 30 can control the hydraulic control valve 31 to realize the remote operation of the shovel 100. Specifically, the controller 30 outputs a control signal corresponding to the content of the remote operation specified by the remote operation signal received from the remote operation support device 400 to the hydraulic control valve 31 through the communication device 60. As a result, the controller 30 can supply a pilot pressure corresponding to the content of the remote operation from the hydraulic control valve 31 to the control valve 17, thereby realizing the operation of the shovel 100 based on the remote operation of the operator.

[0110] Furthermore, when the operating device 26 is an electric type, the controller 30 can supply a pilot pressure corresponding to the operation content (operation signal) of the operating device 26 directly from the hydraulic control valve 31 to the control valve 17, thereby realizing the operation of the shovel 100 based on the operation of the operator.

[0111] The shuttle valve 32 has two inlet ports and one outlet port, and outputs the working oil having the higher pilot pressure of the pilot pressure input to the two inlet ports to the outlet port. Similar to the hydraulic control valve 31, the shuttle valve 32 is provided for each driven element (hydraulic actuator HA) of the operation object of the operating device 26, and is provided for each driving direction of the driven element (hydraulic actuator HA). For example, two shuttle valves 32 are provided for each double-acting hydraulic actuator HA for driving the lower traveling body 1, the upper swing body 3, the boom 4, the arm 5, the bucket 6, etc. One of the two inlet ports of the shuttle valve 32 is connected to the pilot line 27A on the secondary side of the operating device 26 (specifically, the above-mentioned rod device or pedal device included in the operating device 26), and the other is connected to the pilot line 27B on the secondary side of the hydraulic control valve 31. The outlet port of the shuttle valve 32 is connected to the pilot port of the control valve corresponding to the control valve 17 through the pilot line 27. The corresponding control valve is a control valve that drives the hydraulic actuator HA, which is the operating object of the above-mentioned lever device or pedal device connected to one of the inlet ports of the reciprocating valve 32. Therefore, these reciprocating valves 32 can respectively allow the higher pilot pressure of the pilot line 27A on the secondary side of the operating device 26 and the pilot pressure of the pilot line 27B on the secondary side of the hydraulic control valve 31 to act on the pilot port of the corresponding control valve. That is, the controller 30 can control the corresponding control valve regardless of the operation of the operating device 26 by outputting a pilot pressure higher than the pilot pressure on the secondary side of the operating device 26 from the hydraulic control valve 31. As a result, the controller 30 can control the operation of the driven elements (lower traveling body 1, upper swing body 3, boom 4, arm 5 and bucket 6) regardless of the operating state of the operating device 26 by the operator, thereby realizing an automatic operation function or a remote operation function.

[0112] The hydraulic control valve 33 is provided in the pilot line 27A connecting the operating device 26 and the shuttle valve 32. The hydraulic control valve 33 is configured to be able to change its flow path area, for example. The hydraulic control valve 33 operates according to the control signal input from the controller 30. Thus, when the operating device 26 is being operated by the operator, the controller 30 can forcibly reduce the pilot pressure output from the operating device 26. Therefore, even when the operating device 26 is being operated, the controller 30 can forcibly suppress or stop the operation of the hydraulic actuator HA corresponding to the operation of the operating device 26. And, for example, even when the operating device 26 is being operated, the controller 30 can reduce the pilot pressure output from the operating device 26 to be lower than the pilot pressure output from the hydraulic control valve 31. Therefore, the controller 30 can control the hydraulic control valve 31 and the hydraulic control valve 33, for example, regardless of the operation content of the operating device 26, so that the desired pilot pressure can be reliably applied to the pilot port of the control valve in the control valve 17. Thus, the controller 30 can more appropriately implement the automatic operation function or the remote operation function of the shovel 100 by controlling the hydraulic control valve 33 in addition to the hydraulic control valve 31 , for example.

[0113] User Interface System

[0114] like Figure 4 As shown, the user interface system of the excavator 100 includes an operating device 26 , an output device 50 , and an input device 52 .

[0115] The output device 50 outputs various information to the user of the shovel 100 (for example, an operator of the cab 10 or an external remote operator) or people around the shovel 100 (for example, a worker or a driver of a construction vehicle).

[0116] For example, the output device 50 includes a lighting device or a display device that outputs various information in a visual manner. The lighting device is, for example, a warning light (indicator light), etc. The display device is, for example, a liquid crystal display or an organic EL (Electroluminescence) display, etc. For example, Figure 2 As shown, the lighting device or the display device may be installed inside the cab 10, and various information may be outputted visually to the operator inside the cab 10. In addition, the lighting device or the display device may be installed, for example, on the side of the upper swing body 3, and various information may be outputted visually to the operators around the excavator 100.

[0117] Furthermore, the output device 50 may also include a sound output device that outputs various information in an auditory manner (see Figure 7). The sound output device includes, for example, a buzzer or a speaker. The sound output device may be provided at least one of the interior and exterior of the cab 10, and output various information to the operator in the cab 10 or the people (operators, etc.) around the excavator 100 in an auditory manner.

[0118] Furthermore, the output device 50 may include a device that outputs various information by a tactile method such as vibration of the operator's seat.

[0119] The input device 52 receives various inputs from the user of the shovel 100, and inputs signals corresponding to the received inputs to the controller 30. For example, Figure 2 As shown, the input device 52 is provided inside the cab 10 and receives input from an operator or the like inside the cab 10. Alternatively, the input device 52 may be provided on a side surface of the upper swing body 3 and receive input from an operator or the like around the shovel 100.

[0120] For example, the input device 52 includes an operation input device that receives input based on mechanical operation from the user. The operation input device may include a touch panel installed on the display device, a touch pad provided around the display device, a button switch, a lever, a switch key, a knob switch provided on the operation device 26 (lever device), and the like.

[0121] Furthermore, the input device 52 may include a voice input device for accepting voice input from the user. The voice input device includes, for example, a microphone.

[0122] Furthermore, the input device 52 may include a gesture input device that receives gesture input from the user. The gesture input device includes, for example, an imaging device that captures the gesture performed by the user.

[0123] Furthermore, the input device 52 may include a biometric input device for accepting a user's biometric input. The biometric input includes, for example, input of biometric information such as a user's fingerprint or iris.

[0124] Communication Systems

[0125] like Figure 4 As shown, the communication system of the shovel 100 according to the present embodiment includes a communication device 60 .

[0126] The communication device 60 is connected to the external communication line NW and communicates with a device that is separately installed from the shovel 100. The device that is separately installed from the shovel 100 may include a device located outside the shovel 100, and may also include a portable terminal device (mobile terminal) that the user of the shovel 100 brings into the cab 10. The communication device 60 may include, for example, a device that complies with 4G (4 thGeneration: fourth generation), 5G (5 th The communication device 60 may include a mobile communication module of a specification such as the fifth generation (Generation: fifth generation). Furthermore, the communication device 60 may also include a satellite communication module, for example. Furthermore, the communication device 60 may also include a WiFi communication module or a Bluetooth (registered trademark) communication module, for example. Furthermore, when there are multiple connectable communication lines NW, the communication device 60 may also include multiple communication devices in accordance with the type of the communication line NW.

[0127] For example, the communication device 60 communicates with an external device such as the information processing device 200 or the remote operation support device 400 in the construction site through a local communication line built at the construction site. The local communication line is, for example, a mobile communication line based on a local 5G (so-called local 5G) built at the construction site or a local area network based on WiFi6.

[0128] Furthermore, the communication device 60 can communicate with the information processing device 200 or the remote operation support device 400 located outside the construction site via a wide area network which is a wide area communication line including the construction site.

[0129] Control Systems

[0130] like Figure 4 As shown, the control system of the shovel 100 includes a controller 30. Furthermore, the control system of the shovel 100 according to the present embodiment includes an operation pressure sensor 29, a sensor 40, and sensors S1 to S9.

[0131] The controller 30 performs various controls related to the shovel 100 .

[0132] The functions of the controller 30 may be implemented by any hardware or any combination of hardware and software. Figure 3 As shown, the controller 30 includes an auxiliary storage device 30A, a memory device 30B, a CPU (Central Processing Unit) 30C, and an interface device 30D connected via a bus BS1.

[0133] The auxiliary storage device 30A is a nonvolatile storage unit that stores programs to be installed and necessary files and data, etc. The auxiliary storage device 30A is, for example, an EEPROM (Electrically Erasable Programmable Read-Only Memory) or a flash memory.

[0134] For example, when there is a program activation instruction, the memory device 30B loads the program of the auxiliary storage device 30A so that the CPU 30C can read the program. The memory device 30B is, for example, an SRAM (Static Random Access Memory).

[0135] The CPU 30C executes, for example, a program loaded into the memory device 30B, and realizes various functions of the controller 30 according to the commands of the program.

[0136] The interface device 30D functions as, for example, a communication interface for connecting to a communication line inside the shovel 100. The interface device 30D may include a plurality of different types of communication interfaces in accordance with the type of communication line to be connected.

[0137] Furthermore, the interface device 30D functions as an external interface for reading data from a recording medium or writing data to a recording medium. The recording medium is, for example, a dedicated tool connected to a connector provided inside the cab 10 via a detachable cable. Furthermore, the recording medium may be, for example, a general-purpose recording medium such as an SD memory card or a USB (Universal Serial Bus) memory. Thus, a program for realizing various functions of the controller 30 can be provided, for example, by a portable recording medium and installed in the auxiliary storage device 30A of the controller 30. Furthermore, the program can be downloaded from another computer (for example, the information processing device 200) outside the excavator 100 via the communication device 60 and installed in the auxiliary storage device 30A.

[0138] In addition, part of the functions of the controller 30 may be realized by another controller (control device). In other words, the functions of the controller 30 may be realized in a distributed manner by a plurality of controllers mounted on the shovel 100 .

[0139] The operating pressure sensor 29 detects the pilot pressure on the secondary side (pilot line 27A) of the hydraulic pilot operating device 26, that is, the pilot pressure corresponding to the operating state of each driven element (hydraulic actuator) in the operating device 26. The detection signal of the pilot pressure corresponding to the operating state related to each driven element (hydraulic actuator HA) in the operating device 26 detected by the operating pressure sensor 29 is input to the controller 30.

[0140] When the operating device 26 is an electric type, the operating pressure sensor 29 can be omitted. This is because the controller 30 can grasp the operating state of each driven element operated by the operating device 26 based on the operating signal input from the operating device 26 .

[0141] The sensor 40 acquires, for example, measurement data related to the shape of an object around the shovel 100 .

[0142] For example, the sensor 40 is a shape sensor such as a distance measuring sensor or a 3D camera that can obtain measurement data indicating the shape of an object around the shovel 100. Furthermore, the sensor 40 may be a comprehensive sensor such as a multi-wavelength spectroscopic camera that has the function of a characteristic sensor that can obtain measurement data indicating the characteristics of an object around the shovel 100 in addition to the function of a shape sensor.

[0143] For example, Figure 2 As shown, the sensor 40 includes sensors 40F, 40B, 40L, and 40R. The sensor 40F measures the state (shape or characteristics) of an object in front of the upper rotating body 3. The sensor 40B measures the state of an object on the upper rotating body 3. The sensor 40L measures the state of an object on the left of the upper rotating body 3. The sensor 40R measures the state of an object on the right of the upper rotating body 3. Thus, the sensor 40 can measure the state of an object in the entire circumference centered on the excavator 100 when the excavator 100 is viewed from above, that is, across an angular direction range of 360 degrees. Hereinafter, the sensors 40F, 40B, 40L, and 40R are sometimes collectively or individually referred to as "sensors 40X".

[0144] The output data of the sensor 40 (sensor 40X) (i.e., the measured data related to the state of the object around the shovel 100) is input to the controller 30 through a one-to-one communication line or an in-vehicle network. Thus, for example, the controller 30 can grasp the state of the shape or characteristics of the object around the shovel 100 based on the output data of the sensor 40X.

[0145] In addition, part or all of the sensors 40B, 40L, and 40R may be omitted.

[0146] The sensor S1 is mounted on the boom 4 to measure the posture state of the boom 4. The sensor S1 outputs measurement data indicating the posture state of the boom 4. The posture state of the boom 4 is, for example, a posture angle of the base end of the connection portion of the boom 4 with the upper slewing body 3 around the rotation axis (hereinafter referred to as the "boom angle"). The sensor S1 includes, for example, a rotary potentiometer, a rotary encoder, an acceleration sensor, an angular acceleration sensor, a 6-axis sensor, an IMU (Inertial Measurement Unit), etc. The following may also be the same for sensors S2 to S4. Furthermore, the sensor S1 may also include a cylinder sensor for detecting the telescopic position of the boom cylinder 7. The following may also be the same for sensors S2 and S3. The output of the sensor S1 (measurement data indicating the posture state of the boom 4) is input to the controller 30. Thus, the controller 30 can grasp the posture state of the boom 4.

[0147] The sensor S2 is mounted on the boom 5 to measure the posture state of the boom 5. The sensor S2 outputs measurement data indicating the posture state of the boom 5. The posture state of the boom 5 is, for example, a posture angle (hereinafter referred to as "the boom angle") of the base end of the connection portion between the boom 5 and the boom 4 around the rotation axis. The output of the sensor S2 (the measurement data indicating the posture state of the boom 5) is input to the controller 30. Thus, the controller 30 can grasp the posture state of the boom 5.

[0148] The sensor S3 is mounted on the bucket 6 to measure the posture state of the bucket 6. The sensor S3 outputs measurement data indicating the posture state of the bucket 6. The posture state of the bucket 6 is, for example, a posture angle (hereinafter referred to as "arm angle") of the base end of the connection portion between the bucket 6 and the boom 5 around the rotation axis. The output of the sensor S3 (measurement data indicating the posture state of the bucket 6) is input to the controller 30. Thus, the controller 30 can grasp the posture state of the bucket 6.

[0149] The sensor S4 measures the posture state of the body of the excavator 100 (for example, the upper rotating body 3). The sensor S4 outputs measurement data indicating the posture state of the body of the excavator 100. The posture state of the body of the excavator 100 is, for example, the tilt state of the body relative to a predetermined reference plane (for example, a horizontal plane). For example, the sensor S4 is mounted on the upper rotating body 3, and measures the tilt angles of the excavator 100 around two axes in the front-to-back direction and the left-to-right direction (hereinafter referred to as "front-to-back tilt angle" and "left-to-right tilt angle"). The output of the sensor S4 (measurement data indicating the posture state of the body of the excavator 100) is input to the controller 30. Thus, the controller 30 can grasp the posture state (tilt state) of the body (the upper rotating body 3).

[0150] The sensor S5 is mounted on the upper rotating body 3 to measure the rotation state of the upper rotating body 3. The sensor S5 outputs measurement data indicating the rotation state of the upper rotating body 3. The sensor S5 measures, for example, the rotation angular velocity or the rotation angle of the upper rotating body 3. The sensor S5 includes, for example, a gyro sensor, a resolver, a rotary encoder, etc. The output of the sensor S5 (measurement data indicating the rotation state of the upper rotating body 3) is input to the controller 30. Thus, the controller 30 can grasp the rotation state of the upper rotating body 3, such as the rotation angle.

[0151] The controller 30 can grasp (estimate) the position of the tip (bucket 6 ) of the attachment AT based on the outputs of the sensors S1 to S5 .

[0152] In addition, when the sensor S4 includes a gyro sensor, a 6-axis sensor, an IMU, etc. that can detect angular velocity around three axes, the rotation state (for example, rotation angular velocity) of the upper rotating body 3 can also be detected based on the detection signal of the sensor S4. In this case, the sensor S5 can be omitted.

[0153] The sensor S6 measures the position of the excavator 100. The sensor S6 can measure the position in world (global) coordinates or in local coordinates of the construction site. In the former case, the sensor S6 is, for example, a GNSS (Global Navigation Satellite System) sensor. In the latter case, the sensor S6 is a transceiver that can communicate with a device that serves as a reference for the position of the construction site and output a signal corresponding to the position relative to the reference. The output of the sensor S6 is input to the controller 30.

[0154] The sensor S7 measures the pressure (cylinder pressure) of the oil chamber of the boom cylinder 7. The sensor S7 includes, for example, a sensor for measuring the cylinder pressure (rod pressure) of the oil chamber on the rod side of the boom cylinder 7 and a sensor for measuring the cylinder pressure (bottom pressure) of the oil chamber on the bottom side. The output of the sensor S7 (measured data of the cylinder pressure of the boom cylinder 7) is input to the controller 30.

[0155] The sensor S8 measures the pressure (cylinder pressure) of the oil chamber of the boom cylinder 8. The sensor S8 includes, for example, a sensor for measuring the cylinder pressure (rod pressure) of the oil chamber on the rod side of the boom cylinder 8 and a sensor for measuring the cylinder pressure (bottom pressure) of the oil chamber on the bottom side of the boom cylinder 8. The output of the sensor S8 (measurement data of the cylinder pressure of the boom cylinder 8) is input to the controller 30.

[0156] The sensor S9 measures the pressure (cylinder pressure) of the oil chamber of the bucket cylinder 9. The sensor S9 includes, for example, a sensor for measuring the cylinder pressure (rod pressure) of the oil chamber on the rod side of the bucket cylinder 9 and a sensor for measuring the cylinder pressure (bottom pressure) of the oil chamber on the bottom side of the bucket cylinder 9. The output of the sensor S9 (measured data of the cylinder pressure of the bucket cylinder 9) is input to the controller 30.

[0157] The controller 30 can grasp the load state acting on the attachment AT based on the outputs of the sensors S7 to S9. The load acting on the attachment AT includes, for example, the reaction force acting on the bucket 6 from the work object (soil on the ground) or the weight of the soil contained in the bucket 6.

[0158] <Hardware structure of information processing device>

[0159] Figure 5 This is a block diagram showing an example of the hardware configuration of the information processing device 200 .

[0160] The functions of the information processing device 200 are implemented by any hardware or any combination of hardware and software. Figure 5 As shown, the information processing device 200 includes an external interface 201, an auxiliary storage device 202, a memory device 203, a CPU 204, a high-speed operation device 205, a communication interface 206, an input device 207, a display device 208, and a sound output device 209. These are connected via a bus BS2.

[0161] The external interface 201 functions as an interface for reading data from or writing data to the recording medium 201A. The recording medium 201A includes, for example, a floppy disk, a CD (Compact Disc), a DVD (Digital Versatile Disc), a BD (Blu-ray (registered trademark) Disc), an SD memory card, and a USB memory. Thus, the information processing device 200 can read various data used in the processing through the recording medium 201A, store it in the auxiliary storage device 202, or install programs that realize various functions.

[0162] In addition, the information processing device 200 can acquire various data or programs used in processing from an external device via the communication interface 206 .

[0163] The auxiliary storage device 202 stores various installed programs, and stores files and data required for various processes, etc. The auxiliary storage device 202 includes, for example, a HDD (Hard Disc Drive), an SSD (Solid State Disc), a flash memory, and the like.

[0164] When there is an instruction to start the program, the memory device 203 reads and stores the program from the auxiliary storage device 202. The memory device 203 includes, for example, a DRAM (Dynamic Random Access Memory) or an SRAM.

[0165] The CPU 204 executes various programs loaded from the auxiliary storage device 202 to the memory device 203 , and realizes various functions related to the information processing device 200 according to the programs.

[0166] The high-speed computing device 205 performs computing at a relatively high speed in conjunction with the CPU 204. The high-speed computing device 205 includes, for example, a GPU (Graphics Processing Unit), an ASIC (Application Specific Integrated Circuit), or an FPGA (Field-Programmable Gate Array).

[0167] In addition, the high-speed computing device 205 may be omitted depending on the required computing processing speed.

[0168] The communication interface 206 is used as an interface for connecting to external devices so as to enable communication. Thus, the information processing device 200 can communicate with external devices such as the shovel 100 through the communication interface 206. In addition, the communication interface 206 may have multiple communication interfaces depending on the communication method between the connected devices.

[0169] The input device 207 receives various inputs from the user. The input device 207 includes an operating device for remote operation for remotely operating the shovel 100 .

[0170] The input device 207 includes, for example, an input device that receives mechanical operation input from the user (hereinafter referred to as an "operation input device"). The operation device for remote operation may be an operation input device. The operation input device includes, for example, a button, a switch key, a lever, a keyboard, a mouse, a touch panel installed on the display device 208, a touch pad provided separately from the display device 208, and the like.

[0171] Furthermore, the input device 207 may include a voice input device capable of receiving voice input from the user. The voice input device includes, for example, a microphone capable of collecting the user's voice.

[0172] Furthermore, the input device 207 may include a gesture input device capable of receiving gesture input from the user. The gesture input device includes, for example, a camera capable of capturing the gesture of the user.

[0173] Furthermore, the input device 207 may include a biometric input device capable of receiving biometric input from the user. The biometric input device includes, for example, a camera capable of acquiring image data including information related to the user's fingerprint or iris.

[0174] The display device 208 displays an information screen or an operation screen to the user of the information processing device 200. The display device 208 is, for example, a liquid crystal display or an organic EL (Electroluminescence) display.

[0175] The sound output device 209 transmits various information by sound to the user of the information processing device 200. The sound output device 209 is, for example, a buzzer, an alarm, a speaker, or the like.

[0176] [Functional structure of the operation support system]

[0177] Next, in addition to the reference Figure 1 to Figure 5 In addition, refer to Figure 6 , Figure 7 The functional structure of the operation support system SYS will be described.

[0178] <Example 1>

[0179] Figure 6 This is a functional block diagram showing a first example of the functional configuration of the operation support system SYS.

[0180] Hereinafter, the "track of the working part of the excavator 100" is used to mean both the path (i.e., trajectory) along which the working part of the excavator 100 has moved and the path along which it may move in the future. The working part is equivalent to the front end of the AT of the attachment for applying changes to the working object. Specifically, the working part is the bucket 6.

[0181] The shovel 100 includes a support device 150. In this example, the support device 150 performs support related to the execution of the work of the shovel 100 operated based on the autonomous operation function.

[0182] like Figure 6 As shown, in this example, the support device 150 includes a controller 30, a hydraulic control valve 31, a sensor 40, an output device 50, an input device 52, and sensors S1 to S9. Furthermore, when an instruction related to autonomous operation is input from the outside of the excavator 100, the support device 150 may include a communication device 60 instead of the input device 52, or include the communication device 60 in addition to the input device 52.

[0183] The controller 30 includes an operation log providing unit 301 and a work supporting unit 302 as functional units.

[0184] In addition, when there are a plurality of shovels 100 included in the operation support system SYS, there may be a shovel 100 in which the controller 30 includes only the former of the operation log providing unit 301 and the operation support unit 302, and a shovel 100 in which the controller 30 includes only the latter. In this case, the former shovel 100 only has a function of acquiring the operation log of the shovel 100 and providing it to the information processing device 200 for the operation support function of the latter shovel 100. The same may be applied to the case of the second example described later.

[0185] The information processing device 200 includes a log acquisition unit 2001 , a simulator unit 2002 , a log storage unit 2003 , a training data generation unit 2004 , a machine learning unit 2005 , a learned model storage unit 2006 , and a transmission unit 2007 as functional units.

[0186] The operation log providing unit 301 is a functional unit for acquiring an operation log when the shovel 100 performs a predetermined operation and providing the operation log to the information processing device 200 .

[0187] For each type of operation, a plurality of (types of) prescribed actions are predefined. For example, in the case of excavation, the plurality of prescribed actions include excavation, boom raising and rotating, boom lowering and rotating, soil discharge, and brooming. Furthermore, in the case of flat ground operation, the plurality of prescribed actions include excavation, soil discharge, sweeping, horizontal pull-in, rolling, and brooming. Furthermore, in the case of slope operation, the plurality of prescribed actions may include excavation, soil discharge, slope leveling, and rolling. The slope leveling action corresponds to the horizontal pull-in action of flat ground operation, and is an action in which the attachment AT is moved in such a way that the tip of the shovel (claw tip) of the bucket 6 is pulled toward the machine body side (the upper rotating body 3 side) along the slope corresponding to the target construction surface. The sweeping action is, for example, an action in which the attachment AT is operated to push the bucket 6 forward along the ground and sweep the sand and soil forward with the back of the bucket 6. In the sweeping action, for example, the attachment AT performs a lowering action of the boom 4 and an opening action of the dipper stick 5. The horizontal approach action is, for example, an action of smoothing the unevenness of the ground (surface of the terrain) by operating the attachment AT to move the claw tip of the bucket 6 in a manner of being pulled toward the front side approximately horizontally along the ground. In the horizontal approach action, for example, the attachment AT performs an ascending action of the boom 4 and a closing action of the dipper stick 5. The rolling action is, for example, an action of operating the attachment AT to compact the ground with the back side of the bucket 6. Furthermore, the rolling action may be an action of compacting the ground by causing the back side of the bucket 6 to strike the ground while moving the bucket 6 up and down. Furthermore, the rolling action may also be an action of pushing the bucket 6 forward along the ground and sweeping the sand and soil to a predetermined position in front with the back side of the bucket 6, and then compacting the ground at a predetermined position with the back side of the bucket 6. In the rolling action, for example, the attachment AT performs a lowering action of the boom 4 while compacting the ground. The sweeping action is, for example, an action in which the upper revolving body 3 is moved to rotate the bucket 6 left and right in a state along the ground. Furthermore, the sweeping action may be, for example, an action in which the attachment AT and the upper revolving body 3 are moved to rotate the bucket 6 left and right alternately in a state along the ground while pushing the bucket 6 forward. In the sweeping action, for example, the upper revolving body 3 repeats the left and right rotating action alternately. Furthermore, in the sweeping action, for example, in addition to the left and right rotating action of the upper revolving body 3, the attachment AT may also perform the lowering action of the boom 4 and the opening action of the arm 5 as in the case of the sweeping action.

[0188] The operation log of the shovel 100 is time-series data indicating the operation state of the shovel 100. For example, the operation log of the shovel 100 includes time-series data indicating the operation content of the operator. The time-series data indicating the operation content of the operator is, for example, the time-series output data of the operation pressure sensor 29 corresponding to the hydraulic pilot operation device 26 or the time-series output data (operation signal data) of the operation device 26 corresponding to the electric operation device 26. In addition, the operation log of the shovel 100 may be the time-series output data of the sensors S1 to S5 or the time-series data indicating the posture state of the shovel 100 obtained from the output data of the sensors S1 to S5.

[0189] Furthermore, the action log providing unit 301 can obtain an action log when an operator who has a long operating experience and is relatively experienced in the shovel 100 (hereinafter, for convenience, referred to as a "skilled operator") operates the shovel 100, and provide it to the information processing device 200. Thus, as described later, a learned model LM3 capable of reproducing the action of the shovel 100 based on the operation of the skilled operator can be generated based on machine learning based on the action log of the shovel 100.

[0190] The operation log providing unit 301 includes an operation log recording unit 301A, an operation log storage unit 301B, and an operation log transmitting unit 301C.

[0191] The operation log recording unit 301A acquires the operation log when the shovel 100 performs a predetermined operation, and records it in the operation log storage unit 301B. For example, the operation log recording unit 301A records the operation log of the operation in the operation log storage unit 301B every time the shovel 100 performs a predetermined operation.

[0192] The action log of the shovel 100 is stored in the action log storage unit 301B. For example, for each prescribed action performed by the shovel 100, the action log is associated with the data of the time (date and time) when the prescribed action is performed and stored in the action log storage unit 301B. The data of the time when the prescribed action is performed includes the data of both the start and end times of the prescribed action of the shovel 100. Furthermore, when a plurality of prescribed actions are limited, for each prescribed action performed by the shovel 100, the action log, the data of the time when the prescribed action is performed, and the data of the identification information of the prescribed action performed are associated and stored in the action log storage unit 301B. Hereinafter, for the sake of convenience, the data associated with the action log of the shovel 100 is sometimes referred to as "accompanying data". For example, for each prescribed action performed by the shovel 100, the action log storage unit 301B accumulates record data indicating the correspondence between the action log and the accompanying data, thereby constructing a database of the action log when the shovel 100 performs the prescribed action.

[0193] In addition, the operation log of the operation log storage unit 301B that has been sent to the information processing device 200 by the operation log sending unit 301C described later may be deleted afterwards.

[0194] The action log sending unit 301C sends the action log stored in the action log storage unit 301B when the shovel 100 performs a prescribed action and the accompanying data associated with the action log to the information processing device 200 through the communication device 60. In addition, the action log sending unit 301C may send record data indicating the correspondence between the action log of the shovel 100 and the accompanying data for each prescribed action performed by the shovel 100 to the information processing device 200.

[0195] For example, the operation log sending unit 301C sends the operation log of the shovel 100 and the accompanying data which have not been sent and are stored in the operation log storage unit 301B to the information processing device 200 in response to the transmission request of the operation log of the shovel 100 received from the information processing device 200. Furthermore, the operation log sending unit 301C can automatically send the operation log of the shovel 100 and the accompanying data which have not been sent and are stored in the operation log storage unit 301B to the information processing device 200 at a predetermined time. The predetermined time is, for example, when the operation of the shovel 100 is stopped (the key switch is turned "off") or when the operation is started (the key switch is turned "on").

[0196] The log acquisition unit 2001 acquires a log when the shovel 100 performs a predetermined operation.

[0197] The log when the excavator 100 performs the prescribed action includes the action log when the excavator 100 performs the prescribed action and the state log of the work object. The state log of the work object includes the time series data indicating the state of the work object before, during and after the prescribed action of the excavator 100 is performed. The state of the work object includes the shape of the sand (topographic shape) of the work object or the characteristics of the sand, etc. The characteristics of the sand may include, for example, the hardness of the sand, the water content of the sand, the size of the sand particles (grain size), the angle of repose of the sand, etc. The action log when the excavator 100 performs the prescribed action is uploaded from the excavator 100. The state log of the work object when the excavator 100 performs the prescribed action is obtained based on the measurement data uploaded from the sensor group 300 and the accompanying data uploaded from the excavator 100 (data at the time when the prescribed action is performed).

[0198] The state log of the work object may be obtained based on the measurement data of the sensor 40 of the shovel 100. In this case, the measurement data obtained by the sensor 40 during the predetermined operation of the shovel 100 is uploaded from the shovel 100 to the information processing device 200. In this case, the sensor group 300 may be omitted.

[0199] The simulator unit 2002 performs a computer simulation test related to a predetermined operation of the shovel 100 using virtual models of the shovel 100 and a work object (sand and soil).

[0200] For example, the sand and soil of the working object ground is modeled as a collection of tiny particles using the discrete element method (DEM). Thus, the simulator unit 2002 causes the virtual model of the shovel 100 to perform a predetermined action such as an excavation action, and by analyzing the individual movements of the tiny particles, virtually reproduces the behavior of the entire sand and soil of the working object or the reaction force from the sand and soil as a collection.

[0201] The simulator unit 2002 acquires data of the trajectory of the working part of the shovel 100 and data of the state of the working object (sand) before, during, and after the execution of the predetermined action as a log when the shovel 100 executes the predetermined action through the computer simulation test. The former data is equivalent to the action log when the shovel 100 executes the predetermined action through the computer simulation test, and the latter data is equivalent to the state log of the working object when the shovel 100 executes the predetermined action through the computer simulation test.

[0202] The simulator unit 2002 performs a plurality of patterns of computer simulation tests related to the prescribed operation of the shovel 100 using the states of various working objects (sand) and the trajectories of various working parts of the shovel 100. Thus, the simulator unit 2002 can store in the log storage unit 2003 logs of when the shovel 100 performs the prescribed operation under different conditions through the computer simulation tests.

[0203] The log storage unit 2003 stores the logs acquired by the log acquisition unit 2001 and the simulator unit 2002 when the shovel 100 performs the prescribed action in an accumulated manner. For example, the log storage unit 2003 stores the action log of each prescribed action actually performed by the shovel 100 or performed through a computer simulation test, the state log of the work object, and the accompanying data in an associated manner. The log storage unit 2003 may store the logs acquired by the log acquisition unit 2001 and the logs acquired by the simulator unit 2002 in an identifiable manner, or may store them mixedly in an unidentifiable manner.

[0204] The training data generating unit 2004 generates training data for machine learning based on the log stored in the log storage unit 2003 when the shovel 100 performs a predetermined action, and outputs a training data set which is a collection of a plurality of training data. The training data generating unit 2004 may automatically generate the training data by batch processing, or may generate the training data based on input from a user of the information processing device 200. The training data generating unit 2004 includes training data generating units 2004A to 2004C.

[0205] The training data generation unit 2004A generates a training data set for generating a learned model LM1. The learned model LM1 takes the current state of the working object of the shovel 100 and the trajectory of the working part of the shovel 100 until a predetermined time point in the future as input, and infers the future state of the working object of the shovel 100 at a predetermined time point in the future. The training data is a combination of the state of the working object of the shovel 100 at a first time point as input data and the trajectory (track) of the working part of the shovel 100 from the first time point to a second time point later than the first time point, and the state of the working object at the second time point as correct answer data.

[0206] In addition, the training data set for generating the learned model LM1 can be generated only from the log obtained by the log acquisition unit 2001 and the log output from the simulator unit 2002. In this case, the simulator unit 2002 can be omitted. Similarly, the training data set for generating the learned model LM1 can be generated only from the log obtained by the log acquisition unit 2001 and the log output from the simulator unit 2002. In this case, the sensor group 300 and the action log providing unit 301 of the shovel 100 can be omitted. In addition, the training data set for generating the learned model LM1 can include a basic training data set and a final adjustment (fine-tuning) training data set. In this case, since the basic training data set requires a large amount of data, it can be generated based on the log output from the simulator unit 2002, and the final adjustment training data set can also be generated based on the log obtained by the log acquisition unit 2001. The same can be said about the learned models LM2 and LM3 below.

[0207] The training data generation unit 2004B generates training data for generating the learned model LM2. When a plurality of operations are specified, the learned model LM2 is generated for each of the plurality of operations. The learned model LM2 takes data on the state of the work object around the shovel 100 as input, and infers a suitable prescribed action from the plurality of prescribed actions used in the target operation according to the state of the work object corresponding to the input data.

[0208] The training data is, for example, a combination of the state of the work object before the execution of the prescribed action of the shovel 100 as input data and the type of the prescribed action performed by the shovel 100 thereafter as correct answer data. In addition, the training data may also include the target shape of the work object (for example, the target construction surface) as input data. In addition, the training data generation unit 2004B may generate a training data set based on the log obtained by the log acquisition unit 2001 when the shovel 100 performs the prescribed action under the operation of the skilled person. Thus, the learned model LM2 can reproduce the selection method of the prescribed action of the shovel 100 based on the skilled person.

[0209] The training data generating unit 2004C generates training data for generating a learned model LM3. The learned model LM3 is used to infer a target trajectory of a working part of the shovel 100 in a predetermined action by taking data on the state of the working object around the shovel 100 as input. The learned model LM3 is generated for each predetermined action (type) of the shovel 100.

[0210] The learned model LM3, for example, infers the motion parameters of the target trajectory of the working part of the excavator 100 under the prescribed action based on the state of the working object before the execution of the prescribed action of the excavator 100. At this time, the training data is a combination of the state of the working object before the execution of the prescribed action of the excavator 100 as input data and the motion parameters corresponding to the trajectory of the working part when the excavator 100 executes the prescribed action as correct answer data. In addition, the learned model LM3 can infer the target trajectory of the working part of the excavator 100 under the prescribed action based on the state of the working object before the execution of the prescribed action of the excavator 100. In this case, the training data is a combination of the state of the working object before the execution of the prescribed action of the excavator 100 as input data and the trajectory of the working part when the excavator 100 executes the prescribed action as correct answer data. In addition, the training data can also include the target shape of the working object (for example, a target construction surface) as input data. Furthermore, the training data generation unit 2004C can generate a training data set based on the log of the shovel 100 performing a predetermined operation under the operation of the skilled operator acquired by the log acquisition unit 2001. Thus, the learned model LM3 can reproduce the operation of the shovel 100 under the operation of the skilled operator.

[0211] The machine learning unit 2005 generates learned models LM1 to LM3 by performing machine learning on the basic learning model based on the training data set generated by the training data generation unit 2004. The learned model (basic learning model) includes a neural network such as DNN (Deep Neural Network).

[0212] The machine learning unit 2005 includes machine learning units 2005A to 2005C.

[0213] The machine learning unit 2005A performs machine learning on the basic learning model M1 based on the training data set output from the training data generation unit 2004A. Thus, the machine learning unit 2005A can generate a learned model LM1 that can take as input data such as the current state of the working object of the shovel 100 and the target trajectory of the working part of the shovel 100 until a predetermined time point in the future, and output (infer) the state of the working object of the shovel 100 at a predetermined time point in the future. In addition, the machine learning unit 2005A can calibrate (additionally learn) the learned model LM1 so that the error between the inference result based on the learned model LM1 and the actual measurement result of the sensor 40 is reduced. At this time, the data of the result of the inference based on the learned model LM1 and the actual measurement result of the sensor 40 are uploaded from the shovel 100 to the information processing device 200.

[0214] The machine learning unit 2005B performs machine learning on the basic learning model M2 based on the training data set output from the training data generation unit 2004B. As a result, the machine learning unit 2005B can generate a learned model LM2 that can output (infer) one prescribed action from a plurality of prescribed actions corresponding to the target action by taking data on the state of the work object around the shovel 100 before the start of the prescribed action as input. Furthermore, the machine learning unit 2005B can generate the learned model LM2 by performing reinforcement learning using the simulator unit 2002.

[0215] The machine learning unit 2005C performs machine learning on the basic learning model M3 based on the training data set output from the training data generation unit 2004C. Thus, the machine learning unit 2005C can generate a learned model LM3 that can take data on the state of the work object around the shovel 100 as input and output (infer) a target trajectory of the work object in a predetermined action of the shovel 100.

[0216] The learned model storage unit 2006 stores the learned models LM1 and LM2 output by the machine learning unit 2005. When the learned model LM1 is relearned or additionally learned by the machine learning unit 2005A, the learned model LM1 in the learned model storage unit 2006 is updated. The same applies to the case where the learned models LM2 and LM3 are relearned or additionally learned by the machine learning units 2005B and 2005C.

[0217] The transmitting unit 2007 transmits the data of the learned models LM1 to LM3 to the shovel 100 .

[0218] For example, when the learned model LM1 is generated or updated by the machine learning unit 2005A, the transmission unit 2007 transmits the most recently generated or updated learned model LM1 to the shovel 100. Furthermore, the transmission unit 2007 may transmit the latest learned model LM1 in the learned model storage unit 2006 to the shovel 100 in response to a signal requesting the transmission of the learned model LM1 received from the shovel 100. The same may be applied to the learned models LM2 and LM3.

[0219] The work support unit 302 is a functional unit for supporting work of the shovel 100 that is operated by the autonomous operation function.

[0220] The work support unit 302 includes a learned model storage unit 302A, a work object state prediction unit 302B, a motion planning unit 302C, a target trajectory generation unit 302D, and a motion control unit 302E.

[0221] The learned models LM1 and LM2 transmitted from the information processing device 200 and received via the communication device 60 are stored in the learned model storage unit 302A.

[0222] The work object state prediction unit 302B predicts the state of the work object of the shovel 100 at a predetermined time point in the future based on the current state of the work object around the shovel 100 and the target trajectory of the work part of the shovel 100 until a predetermined time point. Specifically, the work object state prediction unit 302B predicts the state of the work object of the shovel 100 at a predetermined time point in the future using the learned model LM1.

[0223] The current state of the working object around the shovel 100 is acquired based on the output of the sensor 40, for example. Furthermore, the current state of the working object around the shovel 100 can be acquired based on the output of the sensors S7 to S9 instead of the sensor 40, or based on the output of the sensors S7 to S9 in addition to the sensor 40. This is because the controller 30 can estimate the reaction force from the ground acting on the bucket 6 from the output of the sensors S7 to S9, and can estimate the state (shape or characteristics) of the sand and soil of the working object from the estimated result of the reaction force. Furthermore, the current state of the working object around the shovel 100 can also be a predicted result of the state of the working object output by the working object state prediction unit 302B itself at an earlier processing time than this time. At this time, for example, the working object state prediction unit 302B predicts the state of the working object based on the initial state of the working object at the start of the work, and uses the predicted result as the current state of the working object afterwards. The initial state of the work object at the start of the work may be provided from outside the shovel 100 , or may be predetermined as a fixed state such as a plane at the same height as the ground on which the lower traveling body 1 of the shovel 100 touches the ground.

[0224] The predetermined time point is, for example, the time at which the correctable predetermined action is started at the nearest time point (time t b ). The modification of the prescribed action, for example, means that the type of the prescribed action to be performed is modified to another type, such as modifying the future prescribed action in an undetermined or provisionally determined state or the excavation action to be performed ... s The time (time t s ). At the delay time τ s For example, the time when the controller 30 transmits the calculation time or calculation result for generating the target trajectory of the bucket 6 or determining the prescribed operation of the shovel 100 to the interface on the control side is included.

[0225] Time t s Using the current time t l and delay time τ s And the calculation is performed using the following formula (1).

[0226] [Formula 1]

[0227] t s =t l +τ s …(1) Delay time τ sIt can be a fixed value or a variable value. In the former case, the fixed value is predetermined, for example, as the maximum value of the delay time assumed according to the processing status of the controller 30. In the latter case, the delay time τ s For example, it may be variable according to a predetermined rule depending on the processing status of the controller 30 such as the load status of the CPU.

[0228] Time t b Equivalent to time t s The start time of the next prescribed action after the prescribed action executed at the time point.

[0229] For example, Figure 7 As shown, at time t s Earlier than the start time of the next action B of the current action A of the shovel 100, the time t b Equivalent to the start time of the next action B of the current action A.

[0230] On the other hand, Figure 8 As shown, at time t s When the next action B of the current action A of the shovel 100 is started later than the start time, the controller 30 starts the operation due to the delay time τ s The next action B cannot be corrected to another type of prescribed action. Therefore, at this time, b Equivalent to time t s The start time of the next action C of the executing action B.

[0231] The motion planning unit 302C calculates the time t based on the result predicted by the work object state prediction unit 302B. b The predicted result of the state of the work object) is planned (determined) from time t b The shovel 100 starts executing a predetermined action (type).

[0232] Thus, the controller 30 can coordinate with the predicted future (time t b ) to determine the type of the prescribed action to be performed by the shovel 100. Therefore, for example, it is not necessary to b The operation of the shovel 100 is stopped for a while, just as the state of the actual working object when the previous predetermined operation is completed determines the subsequent predetermined operation. Therefore, the controller 30 can improve the working efficiency of the shovel 100.

[0233] In addition, the action planning unit 302C may adjust its processing timing so as to plan the next prescribed action of the prescribed action currently being performed by the shovel 100. For example, when the remaining time until the end time of the prescribed action currently being performed by the shovel 100 is greater than the delay time τs, the action planning unit 302C plans the next prescribed action of the shovel 100.

[0234] For example, the action planning unit 302C uses the time t b The prediction result of the state of the working object is determined by using a rule-based method from time t b The type of action to start.

[0235] For example, for each target operation, a plurality of prescribed actions that can be performed are specified, and for each of the plurality of prescribed actions, a change condition of each prescribed action that can be changed is specified in advance. The prescribed actions that can be changed may include the same prescribed actions. This is because the same prescribed actions may be repeated. Then, the action planning unit 302C calculates the change condition of each prescribed action based on the time t. b The success or failure of multiple change conditions starting from the specified action immediately before is determined from time t b The type of action to start.

[0236] For example, Fig. 9 As shown, in the slope work of this example, as a plurality of prescribed actions that can be performed, an excavation action ST1 - 1 , a soil removal action ST1 - 2 , and a slope leveling action ST1 - 3 are prescribed.

[0237] The prescribed actions that can be changed from the standby state ST1-0 corresponding to before the start of the operation and after the completion of the operation are the excavation action ST1-1 and the slope leveling action ST1-3, which are prescribed to their respective change conditions SC1-01 and ST1-03. The change conditions SC1-01 and ST1-03 are mutually opposed conditions. For example, when the difference between the shape of the operation object at the start of the operation and the target shape is less than the prescribed benchmark, the change condition SC1-03 is satisfied, and when it exceeds the prescribed benchmark, the change condition SC1-01 is satisfied. The prescribed action executed at the start of the operation is determined to be the prescribed action corresponding to the change condition that satisfies one of the change conditions SC1-01 and ST1-03.

[0238] The predetermined action that can be changed from the excavation action ST1-1 is the soil removal action ST1-2, and the predetermined change condition SC1-12 is defined. That is, when at time t b When the immediately preceding prescribed action is the excavation action ST1-1, the change condition SC1-12 is always satisfied, and from the time t b The prescribed action to be implemented at the beginning is determined as soil discharge action ST1-2 according to the same principle.

[0239] The prescribed actions that can be changed from the soil removal action ST1-2 are the excavation action ST1-1 and the slope leveling action ST1-3, and the change conditions SC1-21 and SC1-23 are prescribed to them respectively. The change conditions SC1-21 and SC1-23 are mutually opposed conditions. For example, when at time t b When the difference between the predicted result of the shape of the work object and the target shape is less than a predetermined standard, the change condition SC1-23 is satisfied, and when it exceeds the predetermined standard, the change condition SC1-21 is satisfied. b When the previously performed prescribed action is soil discharge action ST1-2, from time t b The prescribed action to be performed is determined to be the prescribed action corresponding to the change condition that satisfies one of the change conditions SC1 - 21 and SC1 - 23 .

[0240] The prescribed actions that can be changed from the slope leveling action ST1-3 are the excavation action ST1-1 and the slope leveling action ST1-3, and the change conditions SC1-31 and SC1-33 are prescribed to them respectively. The change conditions SC1-31 and SC1-33 are mutually opposed conditions. b When the previously performed prescribed action is the slope leveling action ST1-3, from time t b The prescribed action to be performed is determined as the prescribed action corresponding to the change condition that satisfies one of the change conditions SC1 - 31 and SC1 - 33 .

[0241] In addition, when at time t b At the time point t, when the job completion condition indicating that the job has been completed is satisfied, the controller 30 does not execute the predetermined action predetermined in the action planning unit 302C and switches to the standby state (see the dotted arrow in the figure). The job completion condition is, for example, as follows: at time t b The difference between the shape of the work object when the immediately previous work was completed and the target shape is so small that it can be judged to be zero.

[0242] Furthermore, the motion planning unit 302C can determine (the type of) the predetermined motion to be executed by the shovel 100 from the time tb using the learned model LM2 based on the prediction result of the state of the work object at the time tb.

[0243] For example, Fig.10As shown, when performing flat ground operations, there are many defined operations that can be performed, and the combinations of change destinations (in Japanese: 遷移先) for each defined operation become complex. As a result, it may not be possible to appropriately set the change conditions starting from a certain defined operation. In contrast, by using the learned model LM2, even in cases where there are many defined operations that can be performed, such as flat ground operations, and the combinations of change destinations for each defined operation become complex, the motion planning unit 302C can more appropriately determine the defined operation that the excavator 100 starts to execute from time t b onward.

[0244] In addition, when the motion planning unit 302C can only determine the defined operation that the excavator 100 executes from time tb by a rule-based method, the training data generation unit 2004B and the machine learning unit 2005B are omitted.

[0245] The target trajectory generation unit 302D generates the target trajectory of the working part of the excavator 100 under a defined operation based on the state of the work object around the excavator 100. The defined operation at this time is the type of defined operation determined by the motion planning unit 302C.

[0246] For example, the target trajectory generation unit 302D uses the learned model LM3 to generate the target trajectory of the working part after time t s 、t b based on the prediction results (prediction results of the state of the work object at times t s ) predicted by the work object state prediction unit 302B. Thus, for example, the controller 30 can correct the target trajectory of the working part of the excavator 100 in the defined operation in accordance with the state (prediction result) of the work object during the execution of the defined operation. Therefore, the excavator 100 can make the operation of the excavator 100 more appropriate and efficient according to the change of the state of the work object.

[0247] Specifically, the target trajectory generation unit 302D can generate the target trajectory of the working part in the defined operation being executed at the time point of time t s and the target trajectory of the working part in the defined operation starting from time t b onward.

[0248] In addition, the target trajectory generation unit 302D can apply any known method instead of the learned model LM3 to generate the target trajectory of the working part of the excavator 100 in accordance with the state (prediction result) of the work object around the excavator 100. At this time, the training data generation unit 2004C and the machine learning unit 2005C can be omitted. For example, the target trajectory generation unit 302D can be based on the prediction results (time t s,t b The target trajectory generating unit 302B generates the target trajectory data of the working part of the shovel 100 by using MPC (Model Predictive Control). In addition, the target trajectory generating unit 302B may generate the target trajectory data of the working part of the shovel 100 by optimizing the trajectory that is a predetermined reference of the working part of the shovel 100 based on the data related to the characteristics of the sand given in advance.

[0249] The motion control unit 302E causes the shovel 100 to perform a predetermined motion so that a predetermined part of the shovel 100 moves along the target track generated by the target track generation unit 302D. Specifically, the motion control unit 302E controls the hydraulic control valve 31 while grasping the position of the working part based on the output of the sensors S1 to S5, thereby causing the shovel 100 to perform a predetermined motion so that the working part of the shovel 100 moves along the target track. In this way, the shovel 100 can autonomously advance the work while performing the predetermined motion in accordance with the shape of the work object.

[0250] Thus, in this example, the controller 30 determines the future prescribed action of the excavator 100 from a plurality of prescribed actions corresponding to the target operation according to the execution status of the prescribed action of the construction machinery. Specifically, the controller 30 can predict the state of the future operation object according to the execution status of the action of the construction machinery. Moreover, the controller 30 can determine the future prescribed action of the excavator 100 from a plurality of prescribed actions corresponding to the target operation according to the prediction result of the state of the future operation object. Thus, the controller 30 can predetermine the action of the excavator 100 to be performed in the future according to the state of the future operation object. Therefore, the downtime of the excavator 100 when performing the next prescribed action after completing the prescribed action can be suppressed, thereby improving the working efficiency of the excavator 100.

[0251] Furthermore, in this example, after determining the predetermined action of the future shovel 100, the controller 30 generates a target trajectory of the working part corresponding to the determined predetermined action of the shovel 100. Thus, the controller 30 can hierarchically determine the predetermined action of the future shovel 100 and generate the target trajectory of the working part of the future shovel 100 in the predetermined action. Therefore, for example, it is possible to suppress the occurrence of the following situation: when the action plan of the future shovel 100 and the trajectory plan of the working part of the shovel 100 are performed in parallel, the conditions or parameters become huge, and as a result, the action plan and the trajectory plan cannot be performed within a realistic time.

[0252] In addition, part or all of the functions of the work object state prediction unit 302B, the motion planning unit 302C, the target trajectory generation unit 302D, and the motion control unit 302E may be transferred to the information processing device 200. Thus, the processing load of the shovel 100 can be reduced for the processing related to the generation of the target trajectory of the working part of the shovel 100 or the processing related to the control of the motion of the shovel 100.

[0253] <Example 2>

[0254] Fig.11 This is a functional block diagram showing a second example of the functional configuration of the operation support system SYS.

[0255] Hereinafter, the same reference numerals are given to the same or corresponding structures as those in the first example, and the description will be mainly focused on the parts different from the first example.

[0256] Similar to the first example described above, the shovel 100 includes the support device 150. In this example, the support device 150 supports a user who operates the shovel 100 in a semi-automatic operation and performs work.

[0257] like Fig.11 As shown, in this example, similarly to the first example described above, the support device 150 includes the controller 30, the hydraulic control valve 31, the sensor 40, the output device 50, and the sensors S1 to S9. Furthermore, when the excavator 100 is remotely controlled, the support device 150 may include the communication device 60 instead of the input device 52, or may include the communication device 60 in addition to the input device 52.

[0258] Similar to the first example described above, the controller 30 includes an operation log providing unit 301 and a work supporting unit 302 as functional units.

[0259] Similar to the first example described above, the operation log providing unit 301 includes an operation log recording unit 301A, an operation log storage unit 301B, and an operation log transmitting unit 301C.

[0260] Similar to the first example described above, the information processing device 200 includes a log acquisition unit 2001, a simulator unit 2002, a log storage unit 2003, a training data generation unit 2004, a machine learning unit 2005, a learned model storage unit 2006, and a transmission unit 2007 as functional units.

[0261] The work support unit 302 is a functional unit for supporting a user who operates the semi-automatically operated shovel 100 and performs work.

[0262] Similar to the first example, the work support unit 302 includes a learned model storage unit 302A, a work object state prediction unit 302B, an action planning unit 302C, a target trajectory generation unit 302D, and an action control unit 302E. Different from the first example, the work support unit 302 includes an action suggestion unit 302F.

[0263] The action suggestion unit 302F suggests (the type of) the predetermined action of the shovel 100 from time tb determined (planned) by the action planning unit 302C to the user via the output device 50 or the remote operation support device 400 .

[0264] The user selects a prescribed action (type) to be performed by the shovel 100 starting from time tb from a plurality of prescribed actions corresponding to the current operation, based on the suggestion of the prescribed action of the shovel 100 by the action suggestion unit 302F. At this time, the user selects the prescribed action to be performed by the shovel 100 starting from time tb using, for example, the input device 52 or the remote operation support device 400. The result of the selection based on the user is input to the target trajectory generation unit 302D via the input device 52 or the communication device 60.

[0265] The target trajectory generation unit 302D generates a target trajectory of the work site after time ts using the learned model LM3 based on the prediction result (prediction result of the state of the work object at time ts) predicted by the work object state prediction unit 302B.

[0266] Specifically, the target trajectory generation unit 302D can generate a target trajectory of the working part in the prescribed action being performed at the time point ts and a target trajectory of the working part in the prescribed action being performed from the time tb. In this case, the prescribed action to be performed from the time tb is the prescribed action of the shovel 100 corresponding to the above selection result of the user.

[0267] Thus, in this example, the controller 30 determines the prescribed action of the shovel 100 in the future from a plurality of prescribed actions corresponding to the target work based on the prediction result of the state of the future work object, and suggests it to the user through the output device 50 or the remote operation support device 400. Thus, the user can grasp the type of the prescribed action recommended by the shovel 100 based on the prediction result of the state of the future work object before the prescribed action immediately before the recommended prescribed action of the shovel 100 is completed. Therefore, the downtime of the shovel 100 when executing the next prescribed action after completing the prescribed action can be suppressed, thereby improving the working efficiency of the shovel 100.

[0268] In addition, the functions of the action planning unit 302C and the action suggestion unit 302F can also be adopted to the manual operation shovel 100 that realizes all the actions of the shovel 100 through the operation of the operator. In this case, the controller 30 can predict the trajectory of the working part of the shovel 100 in the prescribed action based on the history of the operator's operation content or the output of the sensors S1 to S9, and predict the state of the future work object based on the predicted trajectory. In addition, in the case of remote operation of the shovel 100, part or all of the functions of the learning model storage unit 302A, the work object state prediction unit 302B, the action planning unit 302C, the target trajectory generation unit 302D, the action control unit 302E and the action suggestion unit 302F can be set in the remote operation support device 300. In addition, part or all of the functions of the work object state prediction unit 302B, the action planning unit 302C, the target trajectory generation unit 302D, the action control unit 302E and the action suggestion unit 302F can be transferred to the information processing device 200. Thus, the processing load of the shovel 100 or the remote operation support device 300 can be reduced for the processing related to the generation of the target trajectory of the working part of the shovel 100 or the processing related to the control of the operation of the shovel 100 .

[0269] [Specific example of processing related to autonomous operation of shovel]

[0270] Next, refer to Figure 12 to Figure 17 , a specific example of processing related to the autonomous operation of the shovel 100 is described.

[0271] In this example, Figure 6 The following description is based on the functional structure of the operation support system SYS.

[0272] <Processing related to the start of autonomous operation of the shovel>

[0273] Fig.12 This is a flowchart schematically showing an example of processing related to the start of the autonomous operation of the shovel 100 .

[0274] This flowchart is executed when a user performs a predetermined input related to the start of autonomous operation via the input device 52, the remote operation support device 400, or the remote monitoring support device.

[0275] In step S102, the controller 30 selects a prescribed action to be performed when the autonomous operation of the shovel 100 starts, based on a prescribed input from the user via the input device 52, the remote operation support device 400, or the remote monitoring support device. For example, the controller 30 selects a prescribed action from a plurality of prescribed actions prescribed for target operations such as excavation, leveling, and slope operation. Furthermore, before step S102, the controller 30 may select an operation from a plurality of operations such as excavation, leveling, and slope operation, based on a prescribed input from the user via the input device 52, the remote operation support device 400, or the remote monitoring support device.

[0276] When the process of step S102 is completed, the controller 30 proceeds to step S104 .

[0277] In step S104 , the controller 30 acquires data indicating the state (shape or characteristics) of the sand and soil to be worked on based on the output of the sensor 40 .

[0278] When the process of step S104 is completed, the controller 30 proceeds to step S106 .

[0279] In step S106, the controller 30 (target trajectory generation unit 302D) generates a target trajectory of the bucket 6 related to the predetermined operation of the shovel 100 selected in step S102 at the start of the operation based on the data acquired in step S104. For example, the target trajectory generation unit 302D generates a target trajectory of the working part of the shovel 100 by the same method as step S208 described later.

[0280] When the process of step S106 is completed, the controller 30 proceeds to step S108 .

[0281] In step S108, the controller 30 notifies the user that autonomous operation is possible. For example, the controller 30 notifies the user in the cab 10 or the user around the excavator 100 through the output device 50. In addition, the controller 30 may send a notification signal to the remote operation support device 400 or the remote monitoring support device through the communication device 60, thereby notifying the user using the remote operation support device 400 or the remote monitoring support device.

[0282] When the process of step S108 is completed, the controller 30 proceeds to step S110 .

[0283] In step S110 , the controller 30 starts the autonomous operation of the shovel 100 in accordance with an instruction from the user received via the input device 52 , the remote operation support device 400 , or the remote monitoring support device.

[0284] When the process of step S110 is completed, the controller 30 ends the process of this flowchart.

[0285] In this way, the controller 30 can start the autonomous operation of the shovel 100 according to a predetermined input from the user.

[0286] <Processing related to bucket trajectory generation (main flow)>

[0287] Fig.13 This is a main flowchart schematically showing an example of processing related to generating a bucket trajectory. Fig.14 : is a figure which shows an example of the observation target area TA.

[0288] This flowchart is repeatedly executed every predetermined control cycle after the autonomous operation of the shovel 100 is started.

[0289] In step S202, the controller 30 acquires a future time t that is related to the motion plan and trajectory generation of the shovel 100 and serves as a reference. s and time t b .

[0290] If the process of step S202 is completed, the controller 30 proceeds to step S204.

[0291] In step S204, the work object state prediction unit 302B predicts the time t s and time t b Specifically, the work object state prediction unit 302B calculates the state of the sand and soil of the work object (ground) at the current time t l The state of the sand and soil of the working object and the current time t1 to time t s The target trajectory of the bucket 6 up to the estimated correctable start time t s Similarly, the work object state prediction unit 302B calculates the state of the sand and soil of the work object at the current time t l The state of the sand and soil of the working object and the current time t l To time t b The target trajectory of the bucket 6 up to the time t b The data of the target track of the bucket 6 used in this step is obtained in the process of step S208 of the previous flowchart or in the process of step S209 of the previous flowchart. Figure 8 Obtained during the processing of step S106.

[0292] For example, Fig.14As shown in FIG. 1 , the observation target area TA around the shovel 100 is divided into a predetermined number N of grids. The observation target area TA is an area around the shovel 100 where the work target state prediction unit 302B acquires data indicating the state of the sand. In this example, at time t, the shape h of the sand in each grid i (i=1 to N) of the observation target area TA is determined. t and the characteristics of sandy soil t .

[0293] For example, at the current time t l The shape h of the sand and soil of the working object of the shovel 100 in each grid i of the observation target area TA t and the characteristics of sandy soil t It is represented by the following formulas (2) and (3).

[0294] [Formula 2]

[0295]

[0296] For example, from the current time t l To the correctable start time t s The target trajectory X of bucket 6 until tl:ts and from the current time t l At time t b Target track of bucket 6 X tl:tb It is represented by the following formulas (4) and (5).

[0297] [Formula 3]

[0298]

[0299] That is, in this example, the target trajectory X of the bucket 6 tl:ts The position X of the bucket 6 at each time t is defined as a discrete expression t For example, the position X of bucket 6 at time t t As the posture θ of the boom 4 1,t , the posture θ of the arm 5 2,t , the posture θ of the bucket 6 3,t and the posture θ of the upper rotating body 3 4,t The set of is represented by the following formula (4).

[0300] [Formula 4]

[0301] x t =[θ 1，t ,θ 2,t ,θ 3，t ,θ 4，t ] T …(6)

[0302] Posture θ of boom 41,t For example, it is information indicating the position (rod position) of the boom cylinder 7. 1,t The information may be information indicating the posture angle of the boom 4. The posture θ of the boom 4 1,t The data is obtained based on the output of sensor S7.

[0303] The posture θ of the arm 5 2,t For example, it is information indicating the position of the arm cylinder 8 (rod position). 2,t The information may be information indicating the posture angle of the arm 5. The posture θ of the arm 5 2,t The data is obtained based on the output of sensor S8.

[0304] The posture θ of the bucket 6 3,t For example, it is information indicating the position (rod position) of the bucket cylinder 9. 3,t The information may be information indicating the posture angle of the bucket 6. The posture θ of the bucket 6 3,t The data is obtained based on the output of sensor S9.

[0305] The posture θ of the upper rotating body 3 4,t For example, the information is information indicating the rotation angle of the upper rotating body 3. The posture θ of the upper rotating body 3 4,t The data is obtained based on the output of sensor S4 or sensor S5.

[0306] Furthermore, the position Xt of the bucket 6 may include elements such as information on the speed of each of the boom 4 , the arm 5 , and the bucket 6 , information on the acceleration, and information on the jerk.

[0307] For example, the task state prediction unit 302B calculates the state of each grid i in the observation target area TA at the current time t l The shape of the sand t and the characteristics of sandy soil t And from the current time t l To time t s The target trajectory X of bucket 6 until tl:ts , using the function g corresponding to the learned model LM1, predict the shape h of the sand at time ts ts and the characteristics of sandy soil ts At time t s The shape of the sand ts and the characteristics of sandy soil ts It is represented by the following formula (6).

[0308] [Formula 5]

[0309]

[0310] Similarly, the work object state prediction unit 302B calculates the shape h of the sand and soil at the current time t1 for each grid i in the observation target area TA. t and the characteristics of sandy soil t And from the current time t l At time t b The target trajectory X of bucket 6 until tl:tb , use function g to predict at time t b The shape of the sand tb and the characteristics of sandy soil ts At time t b The shape of the sand tb and the characteristics of sandy soil ts It is represented by the following formula (8).

[0311] [Formula 6]

[0312]

[0313] The function g is constructed, for example, centered around DNN.

[0314] When the process of step S204 is completed, the controller 30 proceeds to step S206 .

[0315] In step S206, the action planning unit 302C performs the following operations based on the current specified action (type) v k-1 and the state of the sand and soil predicted in step S204, and determining the next prescribed action (type) that can be corrected from a plurality of prescribed actions corresponding to the current operation. k .

[0316] For example, the motion planning unit 302C uses the function f corresponding to the learned model LM2 to determine the next correctable prescribed motion v from a plurality of prescribed motions corresponding to the current task. k . Prescribed Actionsv k Using function f, it is expressed by the following equation (9).

[0317] [Formula 7]

[0318]

[0319] Prescribed Actions k 、v k-1 For example, represented by a one-hot vector.

[0320] As described above, the function f is assigned by the learned model LM2, but it may be defined based on a rule instead.

[0321] If the process of step S206 is completed, the controller 30 proceeds to step S208 .

[0322] In step S208, the target trajectory generation unit 302D generates a target trajectory based on the prediction result (time t s The state of the sand at the time of generation t s The target trajectory of the bucket 6 in the subsequent predetermined operation of the shovel 100. Specifically, the target trajectory generation unit 302D generates a target trajectory from time t s At time t b The target trajectory of the bucket 6 in the predetermined operation of the shovel 100 and the time t b The target trajectory of the bucket 6 in the predetermined operation of the shovel 100 until the subsequent predetermined time.

[0323] If the process of step S208 is completed, the controller 30 proceeds to step S210 .

[0324] In step S210 , the target trajectory generation unit 302D writes the data of the target trajectory of the bucket 6 generated in step S208 into a predetermined storage area (address) of the memory device 30B.

[0325] Thus, the operation control unit 302E can access the latest data of the target trajectory of the shovel 100 by accessing a predetermined address of the memory device 30B.

[0326] When the process of step S210 is completed, the controller 30 ends the process of this flowchart.

[0327] Thus, in this example, the controller 30 predicts the future shape of the soil and determines the future predetermined motion of the shovel 100 based on the future shape of the soil. Thus, the controller 30 can generate the target trajectory of the bucket 6 based on the predicted future shape of the soil and the determined future predetermined motion.

[0328] <Processing related to generation of target trajectory (sub-flow)>

[0329] Fig.15 This is a sub-routine diagram schematically showing an example of processing related to the trajectory generation of the bucket 6 . Fig.16 1 is a diagram showing an example of constraint conditions and operation parameters corresponding to a plurality of operation sections of the excavation operation of the shovel 100 .

[0330] Fig.15 The sub-flowchart is equivalent to Fig.13 The process of step S208.

[0331] like Fig.15As shown, in step S302, the target trajectory generation unit 302D selects a restriction function related to the trajectory of the bucket 6 corresponding to the predetermined action (type) of the shovel 100. At this time, the predetermined action of the shovel 100 is at time t s The prescribed action of the shovel 100 being performed at the time point of b Specifically, the target trajectory generation unit 302D selects, for each predetermined action, a restriction function associated with the trajectory of the bucket 6 corresponding to the predetermined action.

[0332] The restriction function (restriction condition) includes, for example, restriction conditions related to the range of motion, speed, or acceleration of the boom cylinder 7, the arm cylinder 8, and the bucket cylinder 9. In addition, the restriction function (restriction condition) may include restriction conditions for preventing obstacles around the excavator 100 from colliding with the bucket 6. Obstacles around the excavator 100 include, for example, people, construction vehicles, other construction machinery, and ground objects (such as fences or utility poles), which can be identified based on the output of the sensor 40.

[0333] If the process of step S302 is completed, the controller 30 proceeds to step S304.

[0334] In step S304, the target trajectory generation unit 302D selects an objective function (cost function) related to the trajectory of the bucket 6 corresponding to the predetermined action (type) of the shovel 100. At this time, as in the case of step S302, the predetermined action of the shovel 100 is at time t s The prescribed action of the shovel 100 being performed at the time point of b Specifically, the target trajectory generation unit 302D selects a cost function related to the trajectory of the bucket 6 corresponding to each predetermined action.

[0335] For example, Fig.16 As shown, the excavation operation as the predetermined operation of the shovel 100 is divided into operation sections of approach, insertion, horizontal excavation, and lifting.

[0336] "Approach" is an action interval for inserting the bucket 6 into the ground and approaching the ground. "Insert" is an action interval after the approach action interval, in which the tip of the bucket 6 contacts the ground and the bucket 6 is inserted to a certain depth in the ground. "Horizontal digging" is an action interval in which the bucket 6 is moved in a substantially horizontal direction after the insert action interval. "Shovel up" is an action interval in which, after horizontal digging, the sand and soil are contained in the bucket 6 and shoveled up to the ground.

[0337] In this example, a cost function related to the speed and acceleration of the bucket 6 or the moving time of the bucket 6 is defined across the entire operation interval from “approaching” to “scooping up”.

[0338] Furthermore, a cost function is specified that is related to the end of an action interval among "approaching", "inserting", "horizontal digging" and "scooping up" or the position of the shovel tip of the bucket 6 in an action interval or the angle of the shovel tip relative to a specified reference (for example, a horizontal plane) and the trajectory of the shovel tip.

[0339] If the process of step S304 is completed, the controller 30 proceeds to step S306 .

[0340] In step S306, the target trajectory generation unit 302D generates a target trajectory according to the prediction result (at time t s ,t b The learned model LM3 is used to estimate the motion parameters of the target trajectory of the bucket 6 in the predetermined motion of the shovel 100 based on the state of the sand and soil of the working object.

[0341] For example, Fig.16 As shown, the motion parameters q1 to q4 for defining the position of the blade tip of the bucket 6 and the motion parameter ρ for defining the angle of the blade tip of the bucket 6 relative to a predetermined reference are defined. 12 , 23 、ρ4.

[0342] The motion parameter q1 is a motion parameter indicating the position of the blade tip of the bucket 6 at the end of "approaching" and the start of "inserting". In this example, a cost function corresponding to the condition for determining whether the position of the blade tip of the bucket 6 at the end of "approaching" and the start of "inserting" is consistent with the position of the motion parameter q1 is defined.

[0343] The action parameter q2 is an action parameter indicating the position of the blade tip of the bucket 6 at the end of "insertion" and the start of "horizontal excavation". In this example, a cost function corresponding to the condition for determining whether the position of the blade tip of the bucket 6 at the end of "insertion" and the start of "horizontal excavation" is consistent with the position of the action parameter q2 is defined.

[0344] Furthermore, in this example, a cost function corresponding to the condition for determining that the position (track) of the blade edge in the "insertion" operation section is located on the straight line defined by the operation parameters q1 and q2 is defined.

[0345] The action parameter q3 is an action parameter indicating the position of the blade tip of the bucket 6 at the end of "horizontal excavation" and the start of "scooping up". In this example, a cost function corresponding to the condition for determining whether the position of the blade tip of the bucket 6 at the end of "horizontal excavation" and the start of "scooping up" is consistent with the position of the action parameter q3 is defined.

[0346] Furthermore, in this example, a cost function corresponding to the condition for determining that the position (track) of the blade tip in the "horizontal excavation" operation section is located on the straight line defined by the operation parameters q2 and q3 is defined.

[0347] The motion parameter q4 is a motion parameter indicating the position of the blade edge of bucket 6 at the end of “scooping up.” In this example, a cost function corresponding to the condition for determining whether the position of the blade edge of bucket 6 at the end of “scooping up” matches the position of the motion parameter q4 is defined.

[0348] Action parameter ρ 12 is an action parameter indicating the angle of the blade tip of the bucket 6 relative to a predetermined reference in the action interval of "insertion". In this example, the angle of the blade tip of the bucket 6 relative to a predetermined reference in the action interval of "insertion" and the action parameter ρ are defined and used to determine the angle of the blade tip of the bucket 6 relative to a predetermined reference in the action interval of "insertion". 12 The restriction function or cost function corresponds to the angle consistency condition.

[0349] Action parameter ρ 23 is an action parameter indicating the angle of the blade tip of the bucket 6 relative to a predetermined reference in the action interval of "horizontal excavation". In this example, the angle of the blade tip of the bucket 6 relative to a predetermined reference in the action interval of "horizontal excavation" and the action parameter ρ are defined and used to determine the angle of the blade tip of the bucket 6 relative to a predetermined reference in the action interval of "horizontal excavation". 23 The restriction function or cost function corresponds to the angle consistency condition.

[0350] The action parameter ρ4 is an action parameter indicating the angle of the blade tip of the bucket 6 relative to a predetermined reference at the end of the "scooping up". In this example, a restriction function or a cost function corresponding to the condition for determining whether the angle of the blade tip of the bucket 6 relative to the predetermined reference at the end of the "scooping up" is consistent with the angle of the action parameter ρ4 is defined.

[0351] If the process of step S306 is completed, the controller 30 proceeds to step S308 .

[0352] In step S308, the target trajectory generation unit 302D calculates the target trajectory of the bucket 6 in the prescribed action of the shovel 100 based on the constraint function and the objective function selected in steps S302 and S304 and the action parameters of the estimated result in step S306. Specifically, the target trajectory generation unit 302D uses a predetermined solver to solve a nonlinear optimization problem with constraints defined by the constraint function and the objective function, and calculates the target trajectory of the bucket 6 in the prescribed action of the shovel 100.

[0353] If the processing of step S308 is completed, the processing of this sub-flowchart ends.

[0354] As described above, in this example, the controller 30 can generate the target trajectory of the shovel 100 using the constraint function and the target function corresponding to the predetermined operation of the shovel 100 .

[0355] In this example, the trajectory of the bucket 6 is represented by relatively few motion parameters. The controller 30 can infer motion parameters defining the trajectory of the bucket 6 using the learned model LM3 based on the prediction result of the state of the soil to be worked in the future.

[0356] <Processing related to excavator motion control>

[0357] Fig.17 This is a flowchart schematically showing an example of processing related to the operation control of the shovel 100 .

[0358] This flowchart is repeatedly executed every predetermined processing cycle during the autonomous operation of the shovel 100 , for example.

[0359] like Fig.17 As shown, in step S402, the operation control unit 302E reads the latest data indicating the target trajectory of the bucket 6 in the predetermined operation of the shovel 100 from a predetermined address of the memory device 30B. Fig.13 The data registered in the process of step S210.

[0360] If the process of step S402 is completed, the controller 30 proceeds to step S404.

[0361] In step S404, the motion control unit 302E controls the motion of the shovel 100 based on the data of the target trajectory of the bucket 6 in the prescribed motion of the shovel 100 read in step S402. Specifically, the motion control unit 302E controls the motion of the shovel 100 while outputting a control command to the hydraulic control valve 31 so that the bucket 6 moves along the target trajectory corresponding to the data read in step S402.

[0362] If the processing of step S404 is completed, the processing of this flowchart ends.

[0363] As described above, in this example, the controller 30 can control the operation of the shovel 100 so as to move along a target trajectory in a predetermined operation of the shovel 100 .

[0364] [Specific example of a method for generating a learned model]

[0365] Next, a specific example of a method for generating the learned model LM1 will be described.

[0366] In this example, the Fig.13The method of generating the function g corresponding to the learned model LM1 used in the processing is explained.

[0367] The training data c of the training data set D generated by the training data generating unit 2004A j (j=1 to L (an integer greater than or equal to 2)) is represented by, for example, the following formula (10).

[0368] [Formula 8]

[0369]

[0370] Training datac j is the input data h^ j , κ^ j , X j and the orbit X as the correct solution data j The shape of the sand when completed r j and the characteristics of sandy soil r j Input data h^ j , κ^ j , X j This corresponds to the input data of the function g in equations (7) and (8).

[0371] As described above, the training data set D may be generated from the logs acquired by the log acquisition unit 2001 , from the logs acquired by the simulator unit 2002 , or from both logs.

[0372] As described above, in the simulator unit 2002, for example, a particle simulation test such as DEM is used, and the height h of the sand is obtained by ray tracing of a shape sensor such as LIDAR virtually arranged relative to the position of the particle. r j .

[0373] Furthermore, as described above, the training data set D may include a basic training data set generated from the log acquired by the simulator unit 2002 and a fine-tuning training data set generated from the log acquired by the log acquisition unit 2001. In this case, the amount of training data included in the fine-tuning training data set may be relatively small.

[0374] As shown in the following formula (11), the function g has a parameter W, and the machine learning is performed by the machine learning unit 2005A in a form in which the parameter W is optimized based on the training data set D.

[0375] [Formula 9]

[0376]

[0377] For example, the parameter W is optimized so that the loss function E(W) of the following equation (12) is minimized, thereby generating a function g corresponding to the learned model LM1.

[0378] [Formula 10]

[0379]

[0380] In this way, the information processing device 200 can generate the training data c j A training data set D is used, and a function g equivalent to the learned model LM1 is generated through machine learning based on the training data set D.

[0381] [effect]

[0382] Next, the functions of the construction machine, information processing device, and program according to the present embodiment will be described.

[0383] In this embodiment, the construction machine includes an operation planning unit. The construction machine is, for example, the shovel 100 described above. The operation planning unit is, for example, the operation planning unit 302C described above. Specifically, the operation planning unit determines the future operation of the construction machine from a plurality of operations based on the execution status of the operation of the construction machine.

[0384] Furthermore, in this embodiment, the information processing device may include an action planning unit. The information processing device is, for example, the controller 30 , the information processing device 200 , or the remote operation support device 400 .

[0385] Furthermore, in this embodiment, in order to realize the function of the action planning unit, the program can cause the information processing device to execute an action planning step. Specifically, in the action planning step, the future action of the construction machine is determined from a plurality of actions according to the execution status of the action of the construction machine. The action planning step is, for example, the above-mentioned step S206.

[0386] Thus, the construction machine or the like can determine the future operation of the construction machine from a plurality of operations in consideration of the state of the work object that changes according to the execution status of the operation of the construction machine. Therefore, the construction machine can realize more appropriate operation.

[0387] Furthermore, in this embodiment, the construction machine or the information processing device may include a prediction unit. The prediction unit is, for example, the above-mentioned work object state prediction unit 302B. Specifically, the prediction unit may predict the future state of the work object based on the execution status of the action of the construction machine. Furthermore, the action planning unit may determine the future action of the construction machine from a plurality of actions based on the prediction result of the future state of the work object predicted by the prediction unit.

[0388] Furthermore, in this embodiment, in order to realize the function of the prediction unit, the program can cause the information processing device to execute the prediction step. Specifically, in the prediction step, the state of the future operation object can be predicted based on the execution status of the operation of the construction machine. Furthermore, in the action planning step, the future operation of the construction machine can be determined from multiple actions based on the prediction result of the state of the future operation object predicted by the prediction unit.

[0389] As a result, the construction machine or the like can determine the future operation of the construction machine from a plurality of operations in accordance with the state of the future work object predicted based on the execution status of the operation of the construction machine.

[0390] Furthermore, in the present embodiment, the prediction unit can predict the future state of the work object based on the trajectory of the work site based on the operation of the construction machine.

[0391] This allows construction machinery and the like to predict the future state of the work object in consideration of changes in the state of the work object that changes in accordance with the trajectory of the work site.

[0392] Furthermore, in this embodiment, the prediction unit can predict the state of the work object after the construction machine's ongoing action or the next action of the ongoing action is completed based on the trajectory of the work part based on the ongoing action of the construction machine or the next action scheduled to be performed. Furthermore, the action planning unit determines the next action of the ongoing action of the construction machine or the next action of the next action scheduled to be performed from multiple actions based on the prediction result of the future state of the work object predicted by the prediction unit.

[0393] Thus, the construction machinery can determine its next action in accordance with the predicted result of the working state after the action being executed by the construction machinery is completed. In addition, the construction machinery can determine the next action after the next action scheduled to be executed in accordance with the predicted result of the working state after the action of the scheduled operation is completed.

[0394] Furthermore, in the present embodiment, the construction machinery and the like may include a generation unit and a control unit. The generation unit may be, for example, the target track generation unit 302D. The control unit may be, for example, the motion control unit 302E. Specifically, the generation unit may generate a track of a working part based on the motion of the construction machinery according to the state of the working object. Furthermore, the control unit may control the motion of the construction machinery so that the working part moves along the track generated by the generation unit. Furthermore, the prediction unit may predict the state of the working object in the future according to the current state of the working object and the track of the working part generated by the generation unit.

[0395] Furthermore, in the present embodiment, in order to realize the functions of the generation unit and the control unit, the program may cause the information processing device to execute the generation step and the control step. The generation step is, for example, the above-mentioned step S208. Specifically, the control step is, for example, the above-mentioned step S404. Specifically, in the generation step, a track of the working part based on the action of the construction machine may be generated according to the state of the working object. Furthermore, in the control step, the action of the construction machine may be controlled so that the working part moves along the track generated in the generation step. Furthermore, in the prediction step, the state of the working object in the future may be predicted based on the current state of the working object and the track of the working part generated in the generation step.

[0396] As a result, a construction machine or the like can predict the state of a future work object based on the trajectory of a work location generated for automatically operating the construction machine.

[0397] Furthermore, in this embodiment, the prediction unit may predict the state of the work object after a predetermined time has passed. Furthermore, the generation unit may generate the trajectory of the work portion after the predetermined time has passed based on the prediction result of the state of the work object after the predetermined time has passed predicted by the prediction unit.

[0398] Thus, for example, a construction machine or the like can generate a trajectory of a work site after a predetermined time has passed, taking into account a delay time from an instruction to control the operation of the construction machine to when the operation can actually be controlled.

[0399] Furthermore, in the present embodiment, the generation unit may generate the trajectory of the work site based on the measurement data of the state of the work object using the target function and the restriction function defined for each of the plurality of actions.

[0400] This allows construction machinery and the like to create tracks for work locations.

[0401] Furthermore, in this embodiment, the trajectory of the working part may be expressed by two or more predetermined number of parameters for each of the plurality of actions. Furthermore, the generating unit may determine the predetermined number of parameters according to the state of the working object to generate the trajectory of the working part.

[0402] This allows construction machinery and the like to create tracks for work locations.

[0403] Furthermore, in the present embodiment, the state of the work object may include at least one of the shape and characteristics of the sand on the surface of the work object.

[0404] This allows construction machinery and the like to predict the future state of the work object in accordance with the shape and characteristics of the soil of the work object.

[0405] Furthermore, in the present embodiment, the construction machine or the like may include a notification unit that notifies an operator of the operation determined by the operation planning unit.

[0406] Furthermore, in this embodiment, the program may cause the support device to execute the action planning step and the notification step. The support device is, for example, the support device 150 or the remote operation support device 300. Specifically, in the action planning step, the future action of the construction machine may be determined from a plurality of actions according to the execution status of the action of the construction machine. Furthermore, in the notification step, the action determined in the action planning step may be notified to the operator of the construction machine.

[0407] Thus, the construction machine or the like can notify the operator of a more appropriate type of action of the construction machine to the operator. Therefore, the operator can operate the construction machine more appropriately. Furthermore, the construction machine or the like can notify the operator of a more appropriate type of action of the construction machine in advance to the operator. Therefore, the operator can start the next action immediately after completing a certain action, and as a result, the working efficiency of the construction machine can be improved.

[0408] As mentioned above, although embodiment is described in detail, this disclosure is not limited to this specific embodiment, Various deformation|transformation and change are possible within the range of the summary described in a claim.

[0409] Finally, this application claims priority based on Japanese patent application No. 2022-186780 filed on November 22, 2022, and the entire contents of the Japanese patent application are incorporated herein by reference.

[0410] Explanation of symbols

[0411] 1-lower walking body, 1C-crawler, 1CL-crawler, 1CR-crawler, 1ML-travel hydraulic motor, 1MR-travel hydraulic motor, 2M-slewing hydraulic motor, 3-upper slewing body, 4-boom, 5-arm, 6-bucket, 7-boom cylinder, 8-arm cylinder, 9-bucket cylinder, 10-operating cab, 30-controller, 31-hydraulic control valve, 32-reciprocating valve, 33-hydraulic control valve, 40-sensor, 50-output device, 52-input device, 60-communication device, 100-excavator, 150-support device, 200-information processing device, 300-sensor group, 301-action log providing unit, 301A-action log recording unit, 301B-action log storage unit, 301C-action log sending unit, 302-operation support unit, 302A-learning completed model storage unit , 302B-work object state prediction unit, 302C-action planning unit, 302D-target trajectory generation unit, 302E-action control unit, 302F-action suggestion unit, 400-remote operation support device, 2001-log acquisition unit, 2002-simulator unit, 2003-log storage unit, 2004-training data generation unit, 2004A-training data generation unit, 2004B-training data generation unit, 2004C-training data generation unit, 2005-machine learning unit, 2005A-machine learning unit, 2005B-machine learning unit, 2005C-machine learning unit, 2006-model storage unit, 2007-transmission unit, AT-attachment, HA-hydraulic actuator, LM1~LM3-learning completed model, NW-communication line, S1~S9-sensor.

Claims

1. A construction machine comprising: The motion planning unit determines the future motion of the construction machine from among a plurality of motions based on the execution status of the motion of the construction machine.

2. The construction machine according to claim 1, comprising: The prediction unit predicts the state of the work object in the future based on the execution status of the operation of the construction machine. The motion planning unit determines the future motion of the construction machine from among the plurality of motions based on the prediction result of the future state of the work object predicted by the prediction unit.

3. The construction machine according to claim 2, wherein: The prediction unit predicts a future state of a work object based on a trajectory of a work location caused by an operation of the construction machine.

4. The construction machine according to claim 3, wherein: The prediction unit predicts the state of the work object after the construction machine completes the ongoing action or the next action of the ongoing action based on the trajectory of the work site based on the ongoing action of the construction machine or the next action scheduled to be performed. The motion planning unit determines, from among the plurality of motions, a next motion of the currently executed motion of the construction machine or a motion immediately following the next motion scheduled to be executed, based on a prediction result of the future state of the work object predicted by the prediction unit.

5. The construction machine according to claim 3 or 4, comprising: a generating unit that generates a trajectory of the working part based on the movement of the construction machine according to the state of the working object; and a control unit to control the movement of the construction machine so that the working part moves along the track generated by the generation unit, The prediction unit predicts a future state of the work object based on a current state of the work object and the trajectory of the work portion generated by the generation unit.

6. The construction machine according to claim 5, wherein: The prediction unit predicts the state of the work object after a predetermined time has passed. The generating unit generates a trajectory of the work site after the predetermined time has passed, based on a prediction result of the state of the work object after the predetermined time has passed predicted by the predicting unit.

7. The construction machine according to claim 5, wherein: The generation unit generates a trajectory of the work site based on the measurement data of the state of the work object using a target function and a restriction function that are predetermined for each of the plurality of actions.

8. The construction machine according to claim 5, wherein: The trajectory of the working part is represented by two or more predetermined number of parameters for each of the plurality of actions. The generating unit determines the predetermined number of parameters according to the state of the work object, thereby generating a trajectory of the work site.

9. The construction machine according to any one of claims 2 to 4, wherein: The state of the work object includes at least one of a shape and a property of sand on the surface of the work object.

10. The construction machine according to any one of claims 1 to 4, comprising: The notification unit notifies the operator of the action determined by the action planning unit.

11. An information processing device comprising: The motion planning unit determines the future motion of the construction machine from among a plurality of motions based on the execution status of the motion of the construction machine.

12. A program causing an information processing device to execute the following steps: The action planning step determines the future action of the construction machine from a plurality of actions based on the execution status of the action of the construction machine.

13. A program that causes a support device to execute the following steps: an action planning step of determining a future action of the construction machine from a plurality of actions according to the execution status of the action of the construction machine; and A notification step of notifying an operator of the construction machine of the action determined in the action planning step.

Images