JP2024072055A - Work machine, information processing device, work support system, program - Google Patents

Abstract

To provide a technology capable of generating a track of a work part of a work machine in accordance with characteristics of work object sediment of the work machine.SOLUTION: A shovel 100 according to an embodiment of the present disclosure is provided with a target track generating unit 302B generating data representing a track of a work part of the shovel 100 based on data regarding characteristics of work object sediment upon predetermined motion of the shovel 100. For example, upon the predetermined motion of the shovel 100, using a learned model which has learned imitation learning through data collected upon the predetermined motion of the shovel 100 through operation by an expert, with data regarding the characteristics of work object sediment as input, the target track generating unit 302 outputs the data representing the track of the work part of the shovel 100.SELECTED DRAWING: Figure 13

Description

This disclosure relates to work machines, etc.

For example, a technology has been disclosed that generates a trajectory for the working part of a work machine when performing a specified operation, depending on the shape of the work target (ground surface) of the work machine and the target shape, etc. (see Patent Document 1).

International Publication No. 2020/032267

However, it is desirable to generate the trajectory of the work area according to the characteristics of the soil being worked on, such as moisture content, grain size, and hardness.

In view of the above problems, the objective is to provide a technology that can generate a trajectory for the working part of a work machine in accordance with the characteristics of the soil and sand that the work machine is working on.

In order to achieve the above object, in one embodiment of the present disclosure,
a generation unit that generates data representing a trajectory of a working portion of the work machine based on data relating to characteristics of soil and sand as a work target during a predetermined operation of the work machine;
A work machine is provided.

In another embodiment of the present disclosure,
A learning model is subjected to supervised learning based on data collected during a predetermined operation of the work machine operated by a predetermined operator, and a learned model is generated that receives data on the characteristics of the soil and sand that is the target of the work machine as an input and outputs data representing the trajectory of a working part of the work machine during the predetermined operation.
An information processing device is provided.

In still another embodiment of the present disclosure,
a first transmission unit provided in the work machine and configured to transmit data relating to characteristics of the soil and sand that is the object of work by the work machine to an information processing device;
a generation unit provided in the information processing device and configured to generate data representing a trajectory of a working portion of the work machine based on data relating to characteristics of the soil and sand during a predetermined operation of the work machine;
a second transmission unit provided in the information processing device and configured to transmit to the work machine a command for controlling the work machine so that the working part moves along the data generated by the generation unit or a trajectory corresponding to the data generated by the generation unit,
A task support system is provided.

In still another embodiment of the present disclosure,
In the information processing device,
executing a generating step of generating data representing a trajectory of a working portion of the work machine based on data relating to characteristics of soil and sand that is a target of work by the work machine during a predetermined operation of the work machine;
The program is provided.

According to the above-described embodiment, the trajectory of the working part of the work machine can be generated according to the characteristics of the soil and sand that the work machine is working on.

FIG. 1 illustrates an example of a work support system. FIG. 2 is a top view showing an example of a shovel. FIG. 2 is a diagram illustrating an example of a configuration for remote control of a shovel. FIG. 2 is a block diagram showing an example of a hardware configuration of a shovel. FIG. 2 illustrates an example of a hardware configuration of an information processing device. FIG. 2 is a functional block diagram showing an example of a functional configuration related to generation of a target trajectory of a working part of a shovel in the work support system. FIG. 2 is a diagram showing a first example of a target trajectory of a working part of a shovel. FIG. 11 is a diagram showing a second example of a target trajectory of a working part of a shovel. FIG. 13 is a diagram showing a third example of a target trajectory of a working part of a shovel. FIG. 13 is a diagram showing a fourth example of a target trajectory of a working part of a shovel. FIG. 13 is a diagram showing an example of a screen showing the progress of work. FIG. 13 is a diagram showing another example of a screen showing the progress of work. 10 is a flowchart illustrating an example of a process for generating a target trajectory of a working portion of a shovel. 11 is a flowchart illustrating an example of a process for updating the progress of a task.

The following describes the embodiment with reference to the drawings.

[Overview of the work support system]
An overview of a work support system SYS according to this embodiment will be described with reference to FIGS. 1 to 3. FIG.

Figure 1 is a diagram showing an example of a work support system SYS. In Figure 1, a left side view of a shovel 100 is shown. Figure 2 is a top view showing an example of the shovel 100. Figure 3 is a diagram showing an example of a configuration related to remote operation of the shovel 100. Below, the direction in which the attachment AT extends when viewed from above the shovel 100 (the upward direction in Figure 2) is defined as "front," and directions on the shovel 100 or directions seen from the shovel 100 may be described.

As shown in FIG. 1, the work support system SYS includes a shovel 100 and an information processing device 200.

The work support system SYS uses the information processing device 200 to cooperate with the shovel 100 and provide support regarding the work of the shovel 100.

The work support system SYS may include one or more excavators 100.

The excavator 100 is a work machine that receives work assistance in the work assistance system SYS.

As shown in Figures 1 and 2, the excavator 100 includes a lower traveling body 1, an upper rotating body 3, an attachment AT including a boom 4, an arm 5, and a bucket 6, and a cabin 10.

The lower traveling body 1 uses crawlers 1C to travel the excavator 100. The crawlers 1C include a left crawler 1CL and a right crawler 1CR. The crawler 1CL is hydraulically driven by a traveling hydraulic motor 1ML. Similarly, the crawler 1CL is hydraulically driven by a traveling hydraulic motor 1MR. This allows the lower traveling body 1 to travel on its own.

The upper rotating body 3 is mounted on the lower traveling body 1 so as to be able to rotate via the rotating mechanism 2. For example, the upper rotating body 3 rotates relative to the lower traveling body 1 when the rotating mechanism 2 is hydraulically driven by the rotating hydraulic motor 2M.

The boom 4 is attached to the front center of the upper rotating body 3 so that it can be raised and lowered around a rotation axis that runs along the left-right direction. The arm 5 is attached to the tip of the boom 4 so that it can rotate around a rotation axis that runs along the left-right direction. The bucket 6 is attached to the tip of the arm 5 so that it can rotate around a rotation axis that runs along the left-right direction.

The bucket 6 is an example of an end attachment and is used, for example, for excavation work and ground leveling work.

The bucket 6 is attached to the tip of the arm 5 in a manner that allows it to be appropriately replaced depending on the work content of the excavator 100. In other words, instead of the bucket 6, a bucket of a different type from the bucket 6 may be attached to the tip of the arm 5. Buckets of a different type from the bucket 6 include, for example, relatively large buckets, buckets for slopes, and buckets for dredging. In addition, a type of end attachment other than a bucket may be attached to the tip of the arm 5. Types of end attachments other than a bucket include, for example, mixers, breakers, and crushers. In addition, a spare attachment such as a quick coupling or a tilt rotator may be provided between the arm 5 and the end attachment.

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

The cabin 10 is a control room where an operator sits and operates the excavator 100. The cabin 10 is mounted, for example, on the front left side of the upper rotating body 3.

For example, the excavator 100 operates driven elements such as the lower traveling body 1 (i.e., a pair of left and right crawlers 1CL, 1CR), upper rotating body 3, boom 4, arm 5, and bucket 6 in response to the operation of an operator in the cabin 10.

In addition to or instead of being configured to be operable by an operator inside the cabin 10, the shovel 100 may be configured to be remotely operable from outside the shovel 100. When the shovel 100 is remotely operated, the inside of the cabin 10 may be unmanned. In the following description, it is assumed that the operation of the operator includes at least one of the operation of the operating device 26 by the operator inside the cabin 10 and the remote operation by an external operator.

For example, as shown in FIG. 3, remote operation includes a mode in which the shovel 100 is operated by operation input related to the actuator of the shovel 100 performed by the remote operation support device 300. The remote operation support device 300 may be provided separately from the information processing device 200, or may be the information processing device 200.

The remote operation support device 300 is provided, for example, in a management center that manages the work of the shovel 100 from the outside. The remote operation support device 300 may also be a portable operation terminal, in which case the operator can remotely operate the shovel 100 while directly checking the work status of the shovel 100 from the vicinity of the shovel 100.

The shovel 100 may transmit, for example, through a communication device 60 described later, an image (hereinafter, "peripheral image") showing the surroundings including the front of the shovel 100 based on an image output by an imaging device (not shown) mounted on the shovel 100 to the remote operation support device 300. The shovel 100 may also transmit an image output by the imaging device to the remote operation support device 300 through the communication device 60, and the remote operation support device 300 may process the image received from the shovel 100 to generate a peripheral image. The remote operation support device 300 may then display a peripheral image showing the surroundings including the front of the shovel 100 on its own display device. Various information images (information screens) for the operator displayed on the output device 50 (display device 50A) inside the cabin 10 of the shovel 100 may also be displayed on the display device of the remote operation support device 300. This allows the operator using the remote operation support device 300 to remotely operate the shovel 100 while checking the display contents of, for example, an image showing the surroundings of the shovel 100 and an information screen displayed on the display device. The excavator 100 may operate actuators and drive driven elements such as the lower traveling body 1, the upper rotating body 3, the boom 4, the arm 5, and the bucket 6 in response to a remote operation signal indicating the content of the remote operation received from the remote operation support device 300 by the communication device 60.

Remote operation may also include a mode in which the shovel 100 is operated by, for example, 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 uttered by surrounding workers and gestures made by workers through a voice input device (e.g., a microphone) or a gesture input device (e.g., an imaging device) mounted on the shovel 100. The shovel 100 may then operate actuators according to the contents of the recognized voices and gestures to drive driven elements such as the lower traveling body 1 (left and right crawlers 1C), upper rotating body 3, boom 4, arm 5, and bucket 6.

The excavator 100 may also automatically operate the actuators regardless of the content of the operator's operation. This allows the excavator 100 to realize a function of automatically operating at least some of the driven elements, such as the lower traveling body 1, the upper rotating body 3, the boom 4, the arm 5, and the bucket 6. This function corresponds to the so-called "automatic driving function" or "MC (Machine Control) function."

The automatic driving function includes, for example, a function for automatically operating driven elements (actuators) other than the driven element (actuator) to be operated in response to an operator's operation of the operating device 26 or remote operation. This function corresponds to a so-called "semi-automatic driving function" or "operation-assisted MC function." The automatic driving function may also include a function for automatically operating at least a portion of the multiple driven elements (actuators) on the assumption that there is no operation of the operating device 26 by the operator or remote operation. This function corresponds to a so-called "fully automatic driving function" or "fully automatic MC function." When the fully automatic driving function is enabled in the excavator 100, the inside of the cabin 10 may be unmanned.

In an automatic driving function such as a semi-automatic driving function or a fully automatic driving function, for example, the operation content of the driven element (actuator) that is the target of automatic driving is automatically determined according to predefined rules. Also, in an automatic driving function such as a semi-automatic driving function or a fully automatic driving function, the excavator 100 may autonomously make various judgments and autonomously determine the operation content of the driven element (actuator) that is the target of automatic driving in accordance with the judgment results.

The work of the shovel 100 may also be remotely monitored. In this case, a remote monitoring support device having the same functions as the remote operation support device 300 may be provided. The remote monitoring support device is, for example, the information processing device 200. This allows a monitor, who is a user of the remote monitoring support device, to monitor the status of the work of the shovel 100 while checking the surrounding image displayed on the display device of the remote monitoring support device. Also, for example, if the monitor determines it is necessary from the standpoint of safety, etc., he or she can use the input device of the remote monitoring support device to make a specified input, thereby intervening in the operation by the operator of the shovel 100 or the fully automatic driving function and bringing the shovel 100 to an emergency stop.

The information processing device 200 communicates with the shovel 100 to cooperate with it and provide support for the work of the shovel 100.

The information processing device 200 is, for example, a server device or a management terminal device installed in a management office in the work site of the shovel 100, or in a management center that manages the operating status of the shovel 100, which is located in a place different from the work site of the shovel 100. The server device may be an on-premise server, a cloud server, or an edge server. The management terminal device may be, for example, a stationary terminal device such as a desktop PC (Personal Computer), or a portable terminal device (mobile terminal) such as a tablet terminal, a smartphone, or a laptop PC. In the latter case, a worker at the work site, a supervisor who supervises the work, a manager who manages the work site, etc. can move around the work site carrying the portable information processing device 200. In the latter case, an operator can, for example, bring the portable information processing device 200 into the cabin of the shovel 100.

The information processing device 200, for example, acquires data on the operating status from the shovel 100. This allows the information processing device 200 to grasp the operating status of the shovel 100 and monitor the presence or absence of abnormalities in the shovel 100. The information processing device 200 can also display data on the operating status of the shovel 100 via the display device 208 described below, allowing the user to confirm the data.

The information processing device 200 may also transmit to the shovel 100 various data such as programs and reference data used in the processing of the controller 30, etc., to the shovel 100. This allows the shovel 100 to perform various processes related to the operation of the shovel 100 using the various data downloaded from the information processing device 200.

[Hardware configuration of work support system]
Next, the hardware configuration of the work support system SYS will be described with reference to FIGS. 4 and 5 in addition to FIGS. 1 to 3.

The hardware configuration of the remote operation support device 300 may be the same as that of the information processing device 200. Therefore, illustrations and descriptions of the hardware configuration of the remote operation support device 300 will be omitted.

<Excavator hardware configuration>
FIG. 4 is a block diagram showing an example of a hardware configuration of the shovel 100.

In Figure 4, the paths through which mechanical power is transmitted are indicated by double lines, the paths through which high-pressure hydraulic oil that drives the hydraulic actuator flows are indicated by solid lines, the paths through which pilot pressure is transmitted are indicated by dashed lines, and the paths through which electrical signals are transmitted are indicated by dotted lines.

The excavator 100 includes various components, such as a hydraulic drive system for hydraulically driving the driven elements, an operation system for operating the driven elements, a user interface system for exchanging information with the user, a communication system for communicating with the outside world, and a control system for various controls. A component may have a function related to only one system and be included in only one system, or may have a function related to multiple systems and be included in each of the systems.

<Hydraulic drive system>
4, the hydraulic drive system of the excavator 100 includes the hydraulic actuators HA that hydraulically drive each of the driven elements such as the lower traveling body 1 (left and right crawlers 1C), the upper rotating body 3, and the attachment AT, as described above. The hydraulic drive system of the excavator 100 according to this embodiment also includes an engine 11, a regulator 13, a main pump 14, and a control valve 17.

The hydraulic actuator HA includes travel hydraulic motors 1ML, 1MR, swing hydraulic motor 2M, boom cylinder 7, arm cylinder 8, and bucket cylinder 9.

In addition, in the shovel 100, some or all of the hydraulic actuators HA may be replaced with electric actuators. In other words, the shovel 100 may be a hybrid shovel or an electric shovel.

The engine 11 is the prime mover of the excavator 100 and the main power source in the hydraulic drive system. The engine 11 is, for example, a diesel engine that uses light oil as fuel. The engine 11 is mounted, for example, at the rear of the upper rotating body 3. The engine 11 rotates at a constant speed at a preset target speed under direct or indirect control by the controller 30 (described later), and drives the main pump 14 and the pilot pump 15.

In addition, other prime movers (e.g., electric motors) may be installed in the excavator 100 instead of or in addition to the engine 11.

The regulator 13 controls (adjusts) the discharge volume 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, the "tilt angle") in response to a control command from the controller 30.

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 rotating body 3, similar 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 tilt angle of the swash plate is adjusted by the regulator 13 to adjust the stroke length of the piston, thereby controlling the discharge flow rate and discharge pressure.

The control valve 17 drives the hydraulic actuators HA in response to the operator's operation of the operating device 26, the contents of remote operation, or operation commands corresponding to the automatic operation function. The control valve 17 is mounted, for example, in the center of the upper rotating body 3. As described above, the control valve 17 is connected to the main pump 14 via a high-pressure hydraulic line, and selectively supplies hydraulic oil supplied from the main pump 14 to each hydraulic actuator in response to the operator's operation or operation commands corresponding to the automatic operation function. Specifically, the control valve 17 includes multiple control valves (also called "directional control valves") that control the flow rate and flow direction of the hydraulic oil supplied from the main pump 14 to each hydraulic actuator HA.

<Controls>
As shown in FIG. 4 , 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 .

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

The pilot pump 15 may be omitted. In this case, the pilot pressure supplied to various hydraulic devices may be generated using the relatively low pressure hydraulic oil after the relatively high pressure hydraulic oil discharged from the main pump 14 is reduced by a specified pressure reducing valve as the base pressure.

The operating device 26 is provided near the cockpit of the cabin 10, and is used by the operator to operate the various driven elements. Specifically, the operating device 26 is used by the operator to operate the hydraulic actuators HA that drive the respective driven elements, and as a result, the operator can operate the driven elements that are the targets of the drive of the hydraulic actuators HA. The operating device 26 includes pedal devices and lever devices for operating the respective driven elements (hydraulic actuators HA).

For example, as shown in FIG. 4, the operating device 26 is of a hydraulic pilot type. Specifically, the operating device 26 uses hydraulic oil supplied from the pilot pump 15 through a pilot line 25A branching from the pilot line 25, and outputs pilot pressure corresponding to the operation to a secondary pilot line 27A. The pilot line 27A is connected to one inlet port of the shuttle valve 32, and is connected to the control valve 17 via a pilot line 27 connected to the outlet port of the shuttle valve 32. As a result, pilot pressure corresponding to the operation of various driven elements (hydraulic actuators HA) in the operating device 26 can be input to the control valve 17 via the shuttle valve 32. Therefore, the control valve 17 can drive each hydraulic actuator HA according to the operation of the operating device 26 by an operator or the like.

The operating device 26 may also be electric. In this case, the pilot line 27A, the shuttle valve 32, and the hydraulic control valve 33 are omitted. Specifically, the operating device 26 outputs an electric signal (hereinafter, "operation signal") according to the operation content, and the operation signal is input to the controller 30. The controller 30 then outputs a control command according to the operation signal, that is, a control signal according to the operation content for the operating device 26, to the hydraulic control valve 31. As a result, a pilot pressure according 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.

The control valves (directional control valves) built into the control valve 17 that drive the hydraulic actuators HA may be of the electromagnetic solenoid type. In this case, the operation signal output from the operating device 26 may be input directly to the control valve 17, i.e., the electromagnetic solenoid type control valve.

Also, as described above, 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 to the electric actuator or a driver that drives the electric actuator according to the operation content of the operating device 26 or the remote operation content specified by the remote operation signal. Also, when the excavator 100 is remotely operated, the operating device 26 may be omitted.

The hydraulic control valve 31 is provided for each driven element (hydraulic actuator HA) to be operated by the operating device 26 and 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 rotating body 3, the boom 4, the arm 5, the bucket 6, etc. The hydraulic control valve 31 may be provided, for example, in the pilot line 25B between the pilot pump 15 and the control valve 17, and may be configured to change its flow area (i.e., the cross-sectional area through which the hydraulic oil can flow). As a result, the hydraulic control valve 31 can output a predetermined pilot pressure to the secondary pilot line 27B using the hydraulic oil of the pilot pump 15 supplied through the pilot line 25B. Therefore, the hydraulic control valve 31 can indirectly apply a predetermined pilot pressure corresponding to a control signal from the controller 30 to the control valve 17 through the shuttle valve 32 between the pilot line 27B and the pilot line 27. Therefore, for example, the controller 30 can supply pilot pressure from the hydraulic control valve 31 to the control valve 17 in response to an operation command corresponding to the automatic driving function, thereby realizing the operation of the excavator 100 using the automatic driving function.

The controller 30 may also control the hydraulic control valve 31 to realize remote operation of the excavator 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 300 to the hydraulic control valve 31 via the communication device 60. As a result, the controller 30 can supply 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 excavator 100 based on the remote operation of the operator.

In addition, when the operating device 26 is electric, the controller 30 causes the hydraulic control valve 31 to directly supply pilot pressure to the control valve 17 according to the operation content (operation signal) of the operating device 26. This allows the controller 30 to realize the operation of the excavator 100 based on the operation of the operator.

The shuttle valve 32 has two inlet ports and one outlet port, and outputs hydraulic oil having the higher pilot pressure of the two pilot pressures input to the inlet ports to the outlet port. The shuttle valve 32 is provided for each driven element (hydraulic actuator HA) to be operated by the operating device 26 and for each driving direction of the driven element (hydraulic actuator HA) in the same manner as the hydraulic control valve 31. For example, two shuttle valves 32 are provided for each double-acting hydraulic actuator HA for driving the lower traveling body 1, the upper rotating 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 secondary pilot line 27A of the operating device 26 (specifically, the above-mentioned lever device and pedal device included in the operating device 26), and the other is connected to the secondary pilot line 27B of the hydraulic control valve 31. The outlet port of the shuttle valve 32 is connected to the pilot port of the corresponding control valve of the control valve 17 through the pilot line 27. The corresponding control valve is a control valve that drives the hydraulic actuator HA that is the object of operation of the lever device or pedal device connected to one inlet port of the shuttle valve 32. Therefore, each of these shuttle valves 32 can apply the higher of the 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 the pilot port of the corresponding control valve. In other words, the controller 30 can control the corresponding control valve regardless of the operator's 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. Therefore, the controller 30 can control the operation of the driven elements (lower traveling body 1, upper rotating body 3, attachment AT) regardless of the operating state of the operating device 26 by the operator, thereby realizing an automatic driving function or a remote operation function.

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 area, for example. The hydraulic control valve 33 operates in response to a control signal input from the controller 30. As a result, the controller 30 can forcibly reduce the pilot pressure output from the operating device 26 when the operating device 26 is operated by the operator. Therefore, even when the operating device 26 is being operated, the controller 30 can forcibly suppress or stop the operation of the hydraulic actuator corresponding to the operation of the operating device 26. In addition, 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, for example, even when the operating device 26 is being operated. Therefore, the controller 30 can reliably apply the desired pilot pressure to the pilot port of the control valve in the control valve 17, for example, regardless of the operation content of the operating device 26, by controlling the hydraulic control valve 31 and the hydraulic control valve 33. Therefore, for example, the controller 30 can more appropriately realize the automatic operation function and remote control function of the excavator 100 by controlling the hydraulic control valve 33 in addition to the hydraulic control valve 31.

<User Interface>
As shown in FIG. 4 , the user interface system of the shovel 100 includes an operation device 26 , an output device 50 , and an input device 52 .

The output device 50 outputs various information to a user of the excavator 100 (e.g., an operator of the cabin 10 or an external remote control operator) and people in the vicinity of the excavator 100 (e.g., a worker or a driver of a work vehicle).

For example, the output device 50 includes lighting equipment and a display device 50A (see FIG. 6) that output various information in a visual manner. The lighting equipment is, for example, a warning light (indicator lamp), etc. The display device 50A is, for example, a liquid crystal display or an organic EL (Electroluminescence) display, etc. For example, as shown in FIG. 2, the lighting equipment and the display device 50A may be provided inside the cabin 10 and output various information in a visual manner to an operator, etc. inside the cabin 10. The lighting equipment and the display device 50A may also be provided on the side of the upper rotating body 3, etc., and output various information in a visual manner to workers, etc. around the excavator 100.

The output device 50 may also include a sound output device that outputs various information by an auditory method. Sound output devices include, for example, a buzzer or a speaker. The sound output device may be provided, for example, inside or outside the cabin 10, and may output various information by an auditory method to an operator inside the cabin 10 or to people around the shovel 100. People around the shovel 100 include, for example, workers performing work around the shovel 100 and operators performing remote operation around the shovel 100.

The output device 50 may also include a device that outputs various information in a tactile manner, such as by vibration of the cockpit.

The input device 52 receives various inputs from the user of the excavator 100, and a signal corresponding to the received input is input to the controller 30. For example, as shown in FIG. 2, the input device 52 is provided inside the cabin 10 and receives inputs from an operator or the like inside the cabin 10. The input device 52 may also be provided on the side of the upper rotating body 3 or the like and receive inputs from workers or the like in the vicinity of the excavator 100.

For example, the input device 52 includes an operation input device that accepts input from a user through mechanical operation. The operation input device may include a touch panel mounted on the display device, a touch pad installed around the display device, a button switch, a lever, a toggle, a knob switch provided on the operation device 26 (lever device), etc.

The input device 52 may also include an audio input device that accepts audio input from the user. The audio input device may include, for example, a microphone.

The input device 52 may also include a gesture input device that accepts gesture input from the user. The gesture input device includes, for example, an imaging device that captures an image of a gesture made by the user.

The input device 52 may also include a biometric input device that accepts biometric input from the user. The biometric input includes, for example, input of biometric information such as the user's fingerprint or iris.

<Communications>
As shown in FIG. 4 , the communication system of the shovel 100 according to this embodiment includes a communication device 60.

The communication device 60 connects to an external communication line and communicates with a device provided separately from the shovel 100. The device provided separately from the shovel 100 may include a device outside the shovel 100, as well as a portable terminal device (mobile terminal) brought into the cabin 10 by a user of the shovel 100. The communication device 60 may include, for example, a mobile communication module conforming to standards such as 4G ( ^4th Generation) and 5G ( ^5th Generation). The communication device 60 may also include, for example, a satellite communication module. The communication device 60 may also include, for example, a WiFi communication module or a Bluetooth (registered trademark) communication module. The communication device 60 may also include a plurality of communication devices in accordance with the communication lines to be connected.

For example, the communication device 60 communicates with external devices such as the information processing device 200 and the remote operation support device 300 at the work site through a local communication line established at the work site. The local communication line is, for example, a local 5G (so-called local 5G) mobile communication line established at the work site or a local network (LAN: Local Area Network) using Wi-Fi6.

The communication device 60 may also communicate with the information processing device 200 and the remote operation support device 300 outside the work site through a wide area communication line that includes the work site, i.e., a wide area network (WAN). Wide area networks include, for example, wide area mobile communication networks, satellite communication networks, and the Internet.

<Control System>
4, the control system of the shovel 100 includes a controller 30. The control system of the shovel 100 according to this embodiment also includes an operating pressure sensor 29, a load state sensor 70, and sensors S1 to S5.

The controller 30 performs various controls related to the excavator 100.

The functions of the controller 30 may be realized by any hardware or any combination of hardware and software. For example, as shown in FIG. 4, the controller 30 includes an auxiliary storage device 30A, a memory device 30B, a CPU (Central Processing Unit) 30C, and an interface device 30D, which are connected by a bus BS1.

The auxiliary storage device 30A is a non-volatile storage means that stores the programs to be installed as well as necessary files and data. The auxiliary storage device 30A is, for example, an EEPROM (Electrically Erasable Programmable Read-Only Memory) or a flash memory.

For example, when an instruction to start a program is received, the memory device 30B loads the program from the auxiliary storage device 30A so that the program can be read by the CPU 30C. The memory device 30B is, for example, a static random access memory (SRAM).

The CPU 30C executes, for example, a program loaded into the memory device 30B and performs various functions of the controller 30 according to the program's instructions.

The interface device 30D functions, for example, as a communication interface for connecting to a communication line inside the excavator 100. The interface device 30D may include multiple different types of communication interfaces according to the type of communication line to be connected.

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

Note that some 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 multiple controllers.

The operating pressure sensor 29 detects the pilot pressure on the secondary side (pilot line 27A) of the hydraulic pilot type operating device 26, i.e., 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 by the operating pressure sensor 29 corresponding to the operating state of each driven element (hydraulic actuator HA) in the operating device 26 is input to the controller 30.

If the operating device 26 is an electrical type, the operating pressure sensor 29 is omitted. This is because the controller 30 can grasp the operating state of each driven element through the operating device 26 based on the operating signal received from the operating device 26.

The load condition sensor 70 detects the load condition acting on the attachment AT. The detection signal of the load condition sensor 70 is input to the controller 30.

The load condition acting on the attachment AT includes, for example, a load condition due to a reaction force acting on the shovel 100 (attachment AT) from the soil and sand that is the work target through the end attachment (bucket 6). The load condition acting on the attachment AT also includes a load condition due to the weight of the soil and sand contained in the bucket 6 when the bucket 6 is in the air separated from the work target.

The load state sensor 70 is, for example, a cylinder pressure sensor provided in at least one of the boom cylinder 7, arm cylinder 8, and bucket cylinder 9. This is because the cylinder pressures of the boom cylinder 7, arm cylinder 8, and bucket cylinder 9 change depending on the load acting on the attachment AT.

The cylinder pressure sensor detects the pressure of the hydraulic oil in the oil chamber on the rod side of the boom cylinder 7, arm cylinder 8, and bucket cylinder 9 (hereinafter referred to as "rod pressure") and the pressure of the hydraulic oil in the oil chamber on the bottom side (hereinafter referred to as "bottom pressure").

The load state sensor 70 may also be a strain gauge attached to the attachment. This is because the load acting on the attachment AT causes strain in the boom cylinder 7, arm cylinder 8, and bucket cylinder 9.

Sensor S1 is attached to the boom 4 and detects the attitude angle (hereinafter referred to as the "boom angle") around the rotation axis of the base end corresponding to the connection part of the boom 4 with the upper rotating body 3. 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 same may be true for sensors S2 to S4 below. Sensor S1 may also include a cylinder sensor that detects the extension/retraction position of the boom cylinder 7. The same may be true for sensors S2 and S3 below. The boom angle detection signal from sensor S1 is taken into controller 30. This allows controller 30 to grasp the attitude state of the boom 4.

Sensor S2 is attached to arm 5 and detects the posture angle (hereinafter "arm angle") around the rotation axis of the base end corresponding to the connection part of arm 5 with boom 4. The arm angle detection signal by sensor S2 is input to controller 30. This allows controller 30 to grasp the posture state of arm 5.

Sensor S3 is attached to bucket 6 and detects the posture angle (hereinafter, "arm angle") around the rotation axis of the base end corresponding to the connection part between bucket 6 and arm 5. The arm angle detection signal by sensor S3 is input to controller 30. This allows controller 30 to grasp the posture state of bucket 6.

The sensor S4 detects the inclination state of the machine body (e.g., the upper rotating body 3) relative to a predetermined reference plane (e.g., a horizontal plane). The sensor S4 is attached, for example, to the upper rotating body 3, and detects the inclination angles (hereinafter, "fore-aft inclination angle" and "left-right inclination angle") about two axes in the fore-aft and left-right directions of the shovel 100 (i.e., the upper rotating body 3). The detection signal corresponding to the inclination angle (fore-aft inclination angle and left-right inclination angle) detected by the sensor S4 is input to the controller 30. This allows the controller 30 to grasp the inclination state of the machine body (upper rotating body 3).

The sensor S5 is attached to the upper rotating body 3 and outputs detection information related to the rotation state of the upper rotating body 3. The sensor S5 detects, for example, the rotation angular velocity and rotation angle of the upper rotating body 3. The sensor S5 includes, for example, a gyro sensor, a resolver, a rotary encoder, etc. The detection information related to the rotation state detected by the sensor S5 is input to the controller 30. This allows the controller 30 to grasp the rotation state, such as the rotation angle, of the upper rotating body 3.

If sensor S4 includes a gyro sensor, a six-axis sensor, an IMU, or the like capable of detecting angular velocity around three axes, the rotation state (e.g., rotation angular velocity) of the upper rotating body 3 may be detected based on the detection signal of sensor S4. In this case, sensor S5 may be omitted.

<Hardware configuration of information processing device>
FIG. 5 is a block diagram showing an example of a hardware configuration of the information processing device 200. As shown in FIG.

The functions of the information processing device 200 are realized by any hardware or any combination of hardware and software. For example, as shown in FIG. 5, 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 calculation device 205, a communication interface 206, an input device 207, a display device 208, and a sound output device 209. The external interface 201, the auxiliary storage device 202, the memory device 203, the CPU 204, the high-speed calculation device 205, the communication interface 206, the input device 207, the display device 208, and the sound output device 209 are connected by a bus BS2.

The external interface 201 functions as an interface for reading data from the recording medium 201A and writing data to the recording medium 201A. Examples of the recording medium 201A include flexible disks, CDs (Compact Discs), DVDs (Digital Versatile Discs), BDs (Blu-ray (registered trademark) Discs), SD memory cards, USB memories, and the like. This allows the information processing device 200 to read various data used in processing through the recording medium 201A, store the data in the auxiliary storage device 202, and install programs that realize various functions.

In addition, the information processing device 200 may obtain various data and programs used in processing from an external device via the communication interface 206.

The auxiliary storage device 202 stores various installed programs as well as files and data necessary for various processes. The auxiliary storage device 202 includes, for example, a hard disk drive (HDD), a solid state disk (SSD), flash memory, etc.

When an instruction to start a program is received, the memory device 203 reads the program from the auxiliary storage device 202 and stores it. The memory device 203 includes, for example, a dynamic random access memory (DRAM) or an SRAM.

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 in accordance with the programs.

The high-speed calculation device 205 works in conjunction with the CPU 204 to perform calculation processing at a relatively high speed. The high-speed calculation device 205 includes, for example, a GPU (Graphics Processing Unit), an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), etc.

The high-speed calculation device 205 may be omitted depending on the required calculation processing speed.

The communication interface 206 is used as an interface for connecting to an external device so as to be able to communicate with the device. This allows the information processing device 200 to communicate with an external device, such as the shovel 100, through the communication interface 206. The communication interface 206 may also have multiple types of communication interfaces depending on the communication method between the connected device, etc.

The input device 207 accepts various inputs from the user.

The input device 207 includes, for example, an input device that accepts mechanical operation input from a user (hereinafter, "operation input device"). The operation input device includes, for example, a button, a toggle, a lever, a keyboard, a mouse, a touch panel implemented in the display device 208, a touch pad provided separately from the display device 208, etc.

The input device 207 may also include a voice input device capable of receiving voice input from a user. The voice input device may include, for example, a microphone capable of collecting the user's voice.

The input device 207 may also include a gesture input device capable of accepting gesture input from a user. The gesture input device includes, for example, a camera capable of capturing an image of the user's gesture.

The input device 207 may also include a biometric input device capable of accepting biometric input from a user. The biometric input device includes, for example, a camera capable of acquiring image data containing information about the user's fingerprint or iris.

The display device 208 displays an information screen and an operation screen for a user of the information processing device 200. The display device 208 is, for example, a liquid crystal display or an organic EL display.

The sound output device 209 conveys various information to the user of the information processing device 200 by sound. The sound output device 209 is, for example, a buzzer, an alarm, a speaker, etc.

[Functional configuration for generating a target trajectory of a working part]
Next, with reference to FIG. 6 in addition to FIGS. 1 to 5, a functional configuration related to generation of a target trajectory of a working part of the shovel 100 in the work support system SYS will be described.

The working part of the shovel 100 refers to the part of the attachment AT (end attachment) that comes into contact with the work target, such as the ground, and performs the actual work when the shovel 100 performs a predetermined operation. For example, when the shovel 100 performs an excavation operation as a predetermined operation, the working part of the shovel 100 is the tip of the bucket 6. Also, for example, when the shovel 100 performs a compaction operation as a predetermined operation, the working part of the shovel 100 is the back surface of the bucket 6.

Figure 6 is a functional block diagram showing an example of the functional configuration related to generating a target trajectory for the working part of the excavator 100 in the work support system SYS.

In the following, the term "trajectory" may be used to include both the path along which the working part of the shovel 100 has already traveled (i.e., the track) and the path along which it may travel in the future.

The shovel 100 includes a support device 150. The support device 150 provides support for the work of the shovel 100.

As shown in FIG. 6, the support device 150 includes an operation device 26, a controller 30, an output device 50, and an input device 52. In addition, when remote operation or remote monitoring of the excavator 100 is performed, the support device 150 may include a communication device 60.

The controller 30 includes, as functional units, an operation log providing unit 301 and a work support unit 302.

When the work support system SYS includes a plurality of shovels 100, there may be shovels 100 in which the controller 30 includes only the operation log providing unit 301 and the work support unit 302, and shovels 100 in which the controller 30 includes only the latter. In this case, the former shovel 100 only has the function of acquiring the operation log of the shovel 100 and providing it to the information processing device 200, which is used for the work support function of the latter shovel 100.

The information processing device 200 includes, as functional units, an operation log acquisition unit 2001, an operation log storage unit 2002, a teacher data generation unit 2003, a machine learning unit 2004, a trained model storage unit 2005, and a distribution unit 2006.

The operation log providing unit 301 acquires the operation log of the shovel 100, which is the original data for realizing the function of generating a target trajectory of the working part of the shovel 100, and provides it to the information processing device 200. Specifically, it acquires an operation log when an operator who has a long history of operating the shovel 100 and is relatively experienced (hereinafter, for convenience, referred to as an "expert") operates the shovel 100, and provides it to the information processing device 200. As a result, the information processing device 200 can cause the base learning model to perform imitation learning of a specific operation of the shovel 100 based on the operation log, and generate a learned model LM that can output a target trajectory of the working part of the shovel 100 corresponding to the operation of the expert.

The operation log of the shovel 100 is data regarding the operation of the shovel 100.

The data relating to the operation of the shovel 100 includes, for example, data representing the operation of the shovel 100. The data representing the operation of the shovel 100 is, for example, data representing the operation content of the operator. The data representing the operation content of the operator is, for example, output data of an operating pressure sensor 29 corresponding to a hydraulic pilot type operating device 26 or output data (operation signal data) of an operating device 26 corresponding to an electric operating device 26. The data representing the operation of the shovel 100 may also be data representing the operating state of the shovel 100 that is actually performed in response to the operation of the operator. The data representing the operating state of the shovel 100 is, for example, output data of sensors S1 to S5, or data representing the posture state of the shovel 100 acquired from the output data of sensors S1 to S5.

In addition, the data regarding the operation of the shovel 100 includes data representing conditions that affect the operation of the shovel 100.

The data representing the conditions that affect the operation of the shovel 100 includes, for example, data regarding the characteristics of the soil that the shovel 100 is working on. The characteristics of the soil include, for example, the grain size of the soil, the moisture content of the soil, and the hardness of the soil. The grain size of the soil is, for example, the diameter of the soil particles.

The data on the characteristics of the soil being worked on is, for example, data on the load state acting on the end attachment (bucket 6) from the soil being worked on. This is because the load acting on the end attachment from the soil being worked on varies depending on the characteristics of the soil being worked on. The data on the load state acting on the end attachment from the soil being worked on is, for example, output data from the load state sensor 70. The data on the characteristics of the soil being worked on may also be output data from a sensor capable of measuring the grain size, moisture content, hardness, etc. of the soil loaded on the shovel 100. The sensor is, for example, a multi-wavelength spectroscopic camera.

The data representing the conditions that affect the operation of the shovel 100 is data representing the weight of the soil contained in the bucket 6 during excavation operation. The data representing the weight of the soil contained in the bucket 6 is, for example, the output data of the load state sensor 70 when the bucket 6 is in the air separated from the work target.

The data representing the conditions that affect the operation of the shovel 100 may also include data representing the working area of the shovel 100. The data representing the working area of the shovel 100 is, for example, setting data for the working area of the shovel 100 that is set in response to a predetermined input received through the input device 52 of the shovel 100.

The data representing the environmental conditions that affect the operation of the shovel 100 may include data representing the target excavation volume of the shovel 100. The data representing the target excavation volume of the shovel 100 is, for example, setting data of the target excavation volume of the shovel 100 that is set in response to a predetermined input received through the input device 52 of the shovel 100. The data representing the target excavation volume of the shovel 100 may also be data obtained by the load state sensor 70 that represents the load state due to the weight of the soil contained in the bucket 6 of the shovel 100 when the bucket 6 is in the air separated from the work target. This is because, when operated by an expert, the difference between the amount of soil ultimately contained in the bucket 6 during the excavation operation and the target excavation volume is considered to be very small.

The operation log providing unit 301 includes an operation log recording unit 301A, an operation log storage unit 301B, and an operation log transmission unit 301C.

The operation log recording unit 301A acquires an operation log related to a specified operation of the shovel 100 and records the operation log in the operation log storage unit 301B. The specified operation is, for example, an excavation operation or a rolling operation. For example, the operation log recording unit 301A records data related to the operation of the shovel 100 in chronological order in the operation log storage unit 301B for each specified operation of the shovel 100.

The operation log storage unit 301B stores the operation log of the shovel 100 in an accumulated form. For example, the operation log storage unit 301B stores data on the operation of the shovel 100 for each predetermined operation of the shovel 100 as time-series data.

In addition, the operation log of the operation log storage unit 301B that has already been transmitted to the information processing device 200 by the operation log transmission unit 301C described below may be erased later.

The operation log transmission unit 301C transmits the operation log of the excavator 100 stored in the operation log memory unit 301B to the information processing device 200 via the communication device 60.

For example, the operation log transmission unit 301C transmits an untransmitted operation log of the shovel 100 stored in the operation log storage unit 301B to the information processing device 200 in response to a signal requesting transmission of the operation log of the shovel 100 from the information processing device 200 (hereinafter, "transmission request signal"). In addition, the operation log transmission unit 301C may automatically transmit an untransmitted operation log of the shovel 100 stored in the operation log storage unit 301B to the information processing device 200 at a predetermined timing. The predetermined timing is, for example, when the shovel 100 stops operating (for example, when the key switch is turned off) or starts operating (for example, when the key switch is turned on).

The operation log acquisition unit 2001 acquires the operation log of the shovel 100 received from the shovel 100.

The operation log acquisition unit 2001 acquires the operation log of the shovel 100 by transmitting a transmission request signal to the shovel 100 in response to an operation by a user of the information processing device 200 or automatically at a predetermined timing. The operation log acquisition unit 2001 may also acquire the operation log of the shovel 100 that is automatically transmitted from the shovel 100 at a predetermined timing.

The operation log memory unit 2002 stores the operation log of the excavator 100 acquired by the operation log acquisition unit 2001 in an accumulated form.

The teacher data generation unit 2003 generates teacher data for machine learning based on the operation log of the excavator 100 in the operation log storage unit 2002, and outputs a teacher data set that is a collection of a large amount of teacher data. Specifically, the teacher data generation unit 2003 generates teacher data for generating a trained model LM, which will be described later. The teacher data is composed of a combination of input data and correct answer data. The teacher data generation unit 2003 may automatically generate teacher data by batch processing, or may generate teacher data in response to input from a user of the information processing device 200.

The machine learning unit 2004 performs machine learning (imitation learning) on the base learning model based on the set of teacher data generated by the teacher data generation unit 2003, and generates a trained model LM. The base learning model includes, for example, a neural network such as a deep neural network (DNN), and is machine-learned by applying an algorithm such as backpropagation, thereby generating the trained model LM.

The machine learning unit 2004 receives data on the characteristics of the soil to be worked on and generates a trained model LM that outputs a target trajectory for the working part of the shovel 100. The machine learning unit 2004 may also update the trained model LM by additional training of the trained model LM or by retraining the base training model.

For example, the machine learning unit 2004 receives as input data on the trajectory (track) of the working part of the shovel 100 from a predetermined time to the most recent time, and data on the characteristics of the soil to be worked on, and generates a learned model LM that outputs a target trajectory of the working part of the shovel 100. The predetermined time is, for example, the start time of a predetermined operation for which the target trajectory is to be generated. The predetermined operation is, for example, an excavation operation or a compaction operation of the shovel 100. The following description focuses on the case where the predetermined operation of the shovel 100 for which the target trajectory is to be generated is an excavation operation.

The machine learning unit 2004 may generate a learned model LM represented by a function g in the following equation (1):

The function g corresponding to the trained model LM receives the trajectory data θ _t-T:t , the reaction force data f _t-T:t , the soil characteristic parameter ε _t-T:t , the target excavation amount l, and the working area parameter a as inputs, and outputs the target trajectory data θ _t+1:t+H , and the soil characteristic parameter ε _t+1:t+H . Time t (t is a positive integer) represents the current time during execution of a predetermined operation. Time t-T (T is a positive integer smaller than t) represents a past time corresponding to a predetermined point in time after the start of a predetermined operation, and represents a time T processing cycles before time t. Time t+1 represents a future time corresponding to the processing cycle immediately after the current time t. Time t+H (H is an integer equal to or greater than 2) represents a future time after time t+1, and represents a time H processing cycles after the current time t.

The trajectory data θ _t-T:t is time series data of the joint angles of the attachment AT corresponding to the trajectory of the working part of the shovel 100 from a past time t-T, which corresponds to a predetermined point in time, to the current time t. The joint angles of the attachment AT are the boom angle, arm angle, and bucket angle. The position of the working part of the end attachment (bucket 6) is determined by determining the boom angle, arm angle, and bucket angle, and the trajectory (trajectory) of the working part of the shovel 100 is determined by the time series of that position. The trajectory data (angle of the attachment AT) θ of the shovel 100 at a certain time may be calculated based on the outputs of the sensors S1 to S5.

The reaction force data f _t-T:t is time-series data of the reaction force acting on the attachment AT (end attachment) from the work target (ground surface) from the past time t-T to the current time t. The reaction force data f of the shovel 100 at a certain time may be calculated based on the output of the load state sensor 70.

The sediment characteristic parameter ε _t-T:t is time-series data of a parameter (sediment characteristic parameter) ε representing the characteristics of the sediment in the work target at the location where the working part of the shovel 100 was in contact from the past time t-T to the current time t. The sediment characteristic parameter ε includes, for example, a parameter representing the grain size of the sediment and a parameter representing the moisture content of the sediment. The sediment characteristic parameter ε _t-T:t is obtained from the output (sediment characteristic parameter ε _t+1:t+H) of the trained model LM of formula (1) in a processing cycle prior to the current time t.

The target excavation amount l is a target value for the amount of soil to be stored in the bucket 6 by one excavation operation. The target excavation amount l of the shovel 100 is set, for example, in response to a predetermined input from a user received through the input device 52. The target excavation amount l of the shovel 100 may also be set in response to a command received from an external device through the communication device 60.

The working area parameter a is a parameter that defines the area to be worked on. The working area parameter a is, for example, a parameter that represents the length in the front-to-rear direction of the working area in front of the shovel 100. The working area parameter a of the shovel 100 is set, for example, in response to a predetermined input from the user that is received through the input device 52. The working area parameter a of the shovel 100 may also be set in response to a command received from an external device through the communication device 60.

The target trajectory data θ _t+1:t+H is time series data of the joint angles of the attachment AT corresponding to the target trajectory of the working part of the shovel 100 from future time t+1 to time t+H, which corresponds to the processing cycle immediately after the current time t.

The soil characteristic parameter ε _t+1:t+H is the soil characteristic parameter ε of the work object at the location where the working part of the shovel 100 is predicted to be in contact from future time t+1 to time t+H, which corresponds to the processing cycle immediately following the current time t.

In this case, the teacher data generation unit 2003 generates input data corresponding to the trajectory data θ _t-T:t , reaction force data f _t-T:t , soil characteristic parameter ε _t-T:t , target excavation amount l, and working area parameter a, based on the operation log of each excavation operation of the shovel 100. Similarly, the teacher data generation unit 2003 generates correct answer data corresponding to the target trajectory data θ _t+1:t+H and soil characteristic parameter ε _t+1:t+H , based on the operation log of each predetermined operation of the shovel 100. Specifically, the teacher data generation unit 2003 generates input data and correct answer data based on the operation log of the same excavation operation of the shovel 100.

More specifically, for each operation log of an excavation operation of the shovel 100, the teacher data generation unit 2003 sets an arbitrary time in the time series data of the operation log of the target excavation operation to the current time t. Then, the teacher data generation unit 2003 generates input data and correct answer data based on the time series data of the operation log of the target excavation operation, i.e., the time series data related to the operation of the shovel 100, using that time as a reference.

For example, the teacher data generating unit 2003 generates input data corresponding to the trajectory data θ _t−T:t , based on data representing the operation of the shovel 100 before a reference time corresponding to time t.

In addition, the teacher data generating unit 2003 generates input data corresponding to the reaction force data f _t-T:t based on data relating to the load state acting on the attachment AT before the reference time corresponding to time t.

Further, the teacher data generating unit 2003 generates input data corresponding to the sediment characteristic parameter ε _t-T:t based on data on the load state acting on the attachment AT for a predetermined period going back from a reference time corresponding to the time t. For example, the teacher data generating unit 2003 generates input data corresponding to the sediment characteristic parameter ε t-T:t using a measurement equation or the like expressing the relationship between the reaction force acting on the tip of the bucket 6 of the shovel 100 and the characteristics of the sediment in the work target with which the tip of the bucket ₆ comes into contact. The measurement equation is obtained in advance, for example, by an experiment, a simulation, or the like using a shovel with the same specifications as the shovel 100. The same may be applied to the sediment characteristic parameter ε _t+1:t+H below.

The teacher data generation unit 2003 also generates input data corresponding to the target excavation volume l based on data representing the target excavation volume of the shovel 100 in the target excavation operation.

The teacher data generation unit 2003 also generates input data corresponding to the working area parameter a based on data representing the working area of the shovel 100 in the target excavation operation.

Furthermore, the teacher data generating unit 2003 generates correct answer data corresponding to the target trajectory data θ _t+1:t+H, based on data representing the operation of the shovel 100 after the reference time corresponding to time t.

In addition, the teacher data generation unit 2003 generates correct data corresponding to the soil characteristic parameter ε _{t+1:t+H, based on data regarding the load state acting on the shovel 100 from the work target during a predetermined period going back from the time corresponding to the time t+H} .

The learned model storage unit 2005 stores the learned model LM generated by the machine learning unit 2004. When the learned model LM is updated by the machine learning unit 2004, the learned model LM after the update is stored in the learned model storage unit 2005. At this time, only the learned model LM after the update may be left in the learned model storage unit 2005, or the learned model LM before the update may coexist with the learned model LM after the update. In the latter case, if there is a problem with the learned model LM after the update, the use of the learned model LM after the update can be stopped and the use of the learned model LM before the update can be restored. In addition, the estimation accuracy of the learned model LM newly generated for updating and the current learned model LM may be verified using test data for verification prepared in advance. For example, the test data for verification is created from a part of the teacher dataset. In addition, the test data for verification may be generated based on an operation log other than the operation log of the excavator 100 used for the teacher data. In this case, the learned model LM may be updated only when verification results show that the estimation accuracy of the newly generated learned model LM is higher than that of the current learned model LM.

The distribution unit 2006 distributes data of the trained model LM to the excavator 100.

For example, when the machine learning unit 2004 generates or updates the trained model LM, the distribution unit 2006 distributes the most recently generated or updated trained model LM to the shovel 100. In addition, the distribution unit 2006 may distribute the latest trained model LM in the trained model memory unit 2005 to the shovel 100 in response to a signal received from the shovel 100 requesting distribution of the trained model LM.

The work support unit 302 supports the work of the excavator 100.

The work support unit 302 includes a learned model storage unit 302A, a target trajectory generation unit 302B, a motion control unit 302C, a work progress recording unit 302D, and a display processing unit 302E.

The trained model storage unit 302A stores the trained model LM that is distributed from the information processing device 200 and received via the communication device 60.

The target trajectory generating unit 302B uses the learned model LM to generate data representing a target trajectory of the working part of the shovel 100 for each predetermined processing cycle during a predetermined operation of the shovel 100. This allows the work support unit 302 to sequentially update the target trajectory of the working part of the shovel 100 in accordance with the characteristics of the soil and sand being worked on for each processing cycle during a predetermined operation of the shovel 100.

The work support unit 302 can generate a target trajectory for the working part of the shovel 100 without using an image of the working area. Therefore, for example, even if the shovel 100 is not equipped with an imaging device that captures the surroundings, the work support unit 302 can generate a target trajectory for the working part of the shovel 100 in accordance with the state of the working area (soil and sand characteristics). Also, for example, even if the reliability of the imaging device mounted on the shovel 100 is low or the shape of the working area around the shovel 100 cannot be properly grasped from the image due to occlusion, the target trajectory for the working part of the shovel 100 can be properly generated.

For example, when the load state acting on the attachment AT (working part) is relatively small with respect to a predetermined threshold value τ _th , the target trajectory generating unit 302B uses the learned model LM to generate data representing a target trajectory of the working part of the shovel 100. "Relatively small with respect to the predetermined threshold value τ _th" may mean that the load state is equal to or smaller than the predetermined threshold value τ _th , or may mean that the load state is smaller than the predetermined threshold value τ _th . On the other hand, when the load state acting on the attachment AT (working part) is relatively large with respect to the predetermined threshold value τ _th , the target trajectory generating unit 302B generates a predetermined trajectory as a target trajectory of the working part of the shovel 100. "Relatively large with respect to the predetermined threshold value τ _th " means that the load state is not relatively small with respect to the predetermined threshold value τ _th . The predetermined trajectory is predefined so that the reaction force acting on the attachment AT (working part) is reduced. The predetermined trajectory is, for example, a trajectory that moves the working part of the shovel 100 in a direction away from the work target (upward). As a result, for example, when the toe of the bucket 6 hits relatively hard ground, rock, or buried object during an excavation operation of the shovel 100, the trajectory of the bucket 6 of the shovel 100 can be corrected so as not to excavate the hard ground, rock, buried object, etc. Hereinafter, a state in which the load state acting on the attachment AT is relatively large with respect to a predetermined threshold value τ _th may be referred to as an "overload state".

Furthermore, when the sediment characteristic parameter ε _t+1:t+H is within the range of the learned sediment characteristic parameter ε of the learned model LM, the target trajectory generating unit 302B may use the learned model LM to generate data representing a target trajectory of the working part of the shovel 100. On the other hand, when the sediment characteristic parameter ε _t+1:t+H is not within the range of the learned sediment characteristic parameter ε of the learned model LM, the target trajectory generating unit 302B generates a predetermined start as a target trajectory of the working part of the shovel 100. The sediment characteristic parameter ε _t+1:t+H being within the range of the learned sediment characteristic parameter ε of the learned model LM means that all of the sediment characteristic parameters ε from time t+1 to time t+H are within the range of the learned sediment characteristic parameter ε of the learned model LM. In addition, the fact that the sediment characteristic parameter ε _t+1:t+H is within the range of the learned sediment characteristic parameter ε of the learned model LM may mean that the ratio of the sediment characteristic parameters ε from time t+1 to time t+H that are within the range of the learned sediment characteristic parameter ε of the learned model LM is equal to or exceeds a predetermined standard. This allows the target trajectory generating unit 302B to generate a predetermined movement as a target trajectory in a situation where it is highly likely that the learned model LM cannot generate a target trajectory that matches the characteristics of the sediment to be worked on. Therefore, it is possible to suppress a situation in which an inappropriate target trajectory is generated for the characteristics of the sediment to be worked on. Hereinafter, the characteristics of the sediment corresponding to the sediment characteristic parameter ε _{t+1:t+H that} is not within the range of the learned sediment characteristic parameter ε of the learned model LM may be referred to as "unlearned sediment characteristics".

The operation control unit 302C outputs a control command to the hydraulic control valve 31 so that the working part of the shovel 100 moves along the target trajectory generated by the target trajectory generating unit 302B, and controls the operation of the shovel 100. Specifically, the operation control unit 302C can operate the shovel 100 so that the working part of the shovel 100 moves along the target trajectory by controlling the hydraulic control valve 31 while grasping the position of the working part of the shovel 100 from the output of the sensors S1 to S5.

For example, the operation control unit 302C controls the operation of the shovel 100 so that the working part of the shovel 100 moves along the target trajectory generated by the target trajectory generating unit 302B without relying on the operation of the operator. That is, the operation control unit 302C controls the operation of the shovel 100 so that the working part of the shovel 100 moves along the target trajectory generated by the target trajectory generating unit 302B by using a fully automatic driving function.

The operation control unit 302C may also control the operation of the shovel 100 so that the working part of the shovel 100 moves along the target trajectory generated by the target trajectory generating unit 302B to assist the operation of the operator. That is, the operation control unit 302C may control the operation of the shovel 100 so that the working part of the shovel 100 moves along the target trajectory generated by the target trajectory generating unit 302B by a semi-automatic operation function. At this time, as described above, the operation of the operator may be the operation of the operator through the operating device 26, or may be remote operation by an operator using the remote operation support device 300 or the like.

The work progress recording unit 302D records the work progress status in a predetermined memory area such as the auxiliary storage device 30A or memory device 30B in accordance with the operation of the excavator 100 based on the control of the operation control unit 302C for the work area input through the input device 52.

For example, when a predetermined operation of the shovel 100 is performed, the work progress recording unit 302D records the change in the shape of the work object based on the trajectory (track) of the working part of the shovel 100 at the time of the predetermined operation, and updates the shape of the work object. At this time, the work progress recording unit 302D may estimate the range in which the work was performed by the predetermined operation, and simply update the shape of the work object by distinguishing whether the work has been performed or not, by recording the part in the work area in which the work was performed. In addition, the work progress recording unit 302D may update the shape of the work object in detail based on the trajectory (track) of the working part of the shovel 100. In this case, the work progress recording unit 302D estimates the change in the shape of the work object based on the trajectory of the working part of the shovel 100 using, for example, a known particle simulation, and updates the shape of the work object. At this time, the particle simulation may use data on the soil characteristic parameter ε generated by the learned model LM during the predetermined operation of the shovel 100.

The work progress recording unit 302D may also record the location in the work area where an overload condition of the attachment AT occurred while the excavator 100 was performing a specified operation.

In addition, the work progress recording unit 302D may record the location in the work area where the sediment characteristic parameter ε _t+1:t+H corresponding to the unlearned sediment characteristics is output while the shovel 100 is performing a specified operation.

The display processing unit 302E displays a screen related to the generation of the target trajectory of the excavator 100 on the display device 50A.

For example, the screen related to generating the target trajectory of the excavator 100 includes a screen showing the shape of the work target that is updated by the work progress recording unit 302D.

The screen for generating the target trajectory of the shovel 100 may also include a screen for enabling or disabling a function for automatically generating a target trajectory for the working part of the shovel 100 via the input device 52 and automatically or semi-automatically moving the working part along the target trajectory.

The screen for generating the target trajectory of the excavator 100 may also include a setting screen that allows the user to set the target excavation volume and working area via the input device 52.

In addition, when the shovel 100 is remotely operated, the display processing unit 302E may transmit data on a screen related to the generation of a target trajectory for the working part of the shovel 100 to the remote operation support device 300 via the communication device 60. This allows the display processing unit 302E to display a screen related to the generation of a target trajectory for the working part of the shovel 100 on the remote operation support device 300 (display device).

[Specific example of the trajectory of the working part of a shovel]
Next, with reference to Figs. 7 to 10, a specific example of a trajectory of the working part of the shovel 100 that is realized by the operation control unit 302C based on the target trajectory generated by the target trajectory generating unit 302B will be described.

<First Example>
FIG. 7 is a diagram showing a first example of a trajectory (trajectory 701) of a working portion of the shovel 100.

Figure 7 includes Figures 7A and 7B.

Figure 7A is a diagram showing the trajectory 701 of the working part (the tip of the bucket 6) during excavation operation of the shovel 100. Figure 7B is a diagram showing the load (reaction force) acting on the attachment AT (bucket 6) corresponding to the trajectory 701 of the working part of the shovel 100 in time series.

As shown in Figures 7A and 7B, at time t11, the toe of the bucket 6 of the shovel 100 penetrates the ground G and the bucket 6 excavates the ground G, and at time t12, the toe of the bucket 6 leaves the ground G and the bucket 6 scoops up the soil.

In this example, as shown in FIG. 7A, the ground G on which the shovel 100 is to work has a relatively flat shape. Also, in this example, the ground G on which the shovel 100 is to work has the characteristic that the soil is relatively soft throughout the entire working area. Therefore, the work support unit 302 generates a smooth target trajectory throughout the entire excavation operation in accordance with the characteristics of the substantially flat ground and the substantially uniform soil, and causes the shovel 100 to perform an excavation operation so that the toe of the bucket 6 moves along the target trajectory. As a result, the shovel 100 can perform an excavation operation by moving the toe of the bucket 6 on a smooth trajectory 701 throughout the entire working area in accordance with the characteristics of the substantially flat ground and the substantially uniform soil.

Specifically, the trajectory 701 of the toe of the bucket 6 increases the depth of the toe of the bucket 6 relative to the ground G (hereinafter, "digging depth") in the first half of the excavation operation of the shovel 100 so that the load acting on the bucket 6 increases relatively gradually. Then, the trajectory 701 of the toe of the bucket 6 decreases the digging depth of the bucket 6 relative to the ground G in the second half of the excavation operation of the shovel 100 so that the load acting on the bucket 6 decreases relatively gradually.

As shown in Figures 7A and 7B, the load acting on the bucket 6 after the bucket 6 has been lifted above the ground surface G at the completion of the excavation operation is smaller than the load acting on the bucket 6 before the bucket 6 is inserted into the ground surface G at the start of the excavation operation. This is because, at the completion of the excavation operation of the shovel 100, the bucket 6 contains soil that has been collected by the excavation operation, and a load due to the weight of the soil acts on the bucket 6.

In this example, as shown in FIG. 7B, the absolute value of the load acting on the bucket 6 during the excavation operation of the shovel 100 is relatively small. This is because the soil on the ground G is relatively soft, as described above. For this reason, as shown in FIG. 7A, the work support unit 302 generates a target trajectory for the toe of the bucket 6 so that the digging depth of the bucket 6 is relatively large, and causes the shovel 100 to perform an excavation operation so that the toe of the bucket 6 moves along the target trajectory. As a result, the shovel 100 can perform an excavation operation by moving the toe of the bucket 6 along a trajectory 701 with a relatively large digging depth in accordance with the characteristics of the soil on the relatively soft ground G.

In this way, in this example, the work support unit 302 can generate a relatively smooth target trajectory for the tip of the bucket 6 in accordance with the generally flat shape and generally uniform characteristics of the soil and sand throughout the entire work area. Therefore, the excavator 100 can perform an excavation operation by moving the tip of the bucket 6 on a trajectory 701 that corresponds to the relatively smooth target trajectory throughout the entire excavation operation.

In addition, in this example, the work support unit 302 can generate a target trajectory for the tip of the bucket 6, which has a relatively large digging depth, in accordance with the characteristics of the relatively soft soil and sand on the ground G in the work area. Therefore, the excavator 100 can move the tip of the bucket 6 on a trajectory 701, which has a relatively large digging depth, in accordance with the characteristics of the relatively soft soil and sand on the ground G in the work area, and perform an excavation operation.

<Second Example>
FIG. 8 is a diagram showing a second example of the trajectory of the working portion of the shovel 100 (trajectory 801).

Figure 8 includes Figures 8A and 8B.

Figure 8A is a diagram showing the trajectory 801 of the working part (the tip of the bucket 6) during excavation operation of the shovel 100. Figure 8B is a diagram showing the load (reaction force) acting on the attachment AT (bucket 6) corresponding to the trajectory 801 of the working part of the shovel 100 in time series.

As shown in Figures 8A and 8B, at time t21, the toe of the bucket 6 of the shovel 100 penetrates the ground G and the bucket 6 excavates the ground G, and at time t22, the toe of the bucket 6 leaves the ground G and the bucket 6 scoops up the soil.

As shown in FIG. 8A, in this example, as in the first example described above, the ground G on which the shovel 100 is to work has a relatively flat shape. Also, in this example, unlike the first example described above, the ground G on which the shovel 100 is to work has the characteristic that the soil is relatively hard throughout the entire working area. Therefore, the work support unit 302 generates a smooth target trajectory throughout the entire excavation operation in accordance with the characteristics of the substantially flat ground and the substantially uniform soil, and causes the shovel 100 to perform the excavation operation so that the toe of the bucket 6 moves along the target trajectory. As a result, the shovel 100 can perform the excavation operation by moving the toe of the bucket 6 on a smooth trajectory 801 throughout the entire excavation operation in accordance with the characteristics of the substantially flat ground and the substantially uniform soil.

In this example, as shown in FIG. 8B, the absolute value of the load acting on the bucket 6 during the excavation operation of the shovel 100 is relatively large. This is because the soil on the ground G is relatively hard. For this reason, the work support unit 302 generates a target trajectory for the toe of the bucket 6 so that the digging depth of the bucket 6 is relatively small, and causes the shovel 100 to perform the excavation operation so that the toe of the bucket 6 moves along the target trajectory. As a result, the shovel 100 can perform the excavation operation by moving the toe of the bucket 6 along a trajectory 801 with a relatively small digging depth in accordance with the characteristics of the soil on the relatively hard ground G.

In this way, in this example, similar to the first example described above, the work support unit 302 can generate a relatively smooth target trajectory for the tip of the bucket 6 in accordance with the generally flat shape and generally uniform characteristics of the soil throughout the entire work area. Therefore, the excavator 100 can perform an excavation operation by moving the tip of the bucket 6 on a trajectory 801 that corresponds to the relatively smooth target trajectory throughout the entire excavation operation.

In addition, in this example, the work support unit 302 can generate a target trajectory for the tip of the bucket 6 with a relatively small digging depth in accordance with the characteristics of the hard soil and sand on the ground G in the work area. Therefore, the excavator 100 can move the tip of the bucket 6 on a trajectory 801 with a relatively large digging depth in accordance with the characteristics of the relatively hard soil and sand on the ground G in the work area, and perform an excavation operation.

<Third Example>
FIG. 9 is a diagram showing a third example of the trajectory of the working portion of the shovel 100 (trajectory 901).

Figure 9 includes Figures 9A and 9B.

Figure 9A is a diagram showing the trajectory 901 of the working part (the tip of the bucket 6) during an excavation operation of the shovel 100. Figure 9B is a diagram showing the load (reaction force) acting on the attachment AT (bucket 6) corresponding to the trajectory 901 of the working part of the shovel 100 in time series.

As shown in Figures 9A and 9B, at time t31, the toe of the bucket 6 of the shovel 100 penetrates the ground G and the bucket 6 excavates the ground G, and at time t32, the toe of the bucket 6 leaves the ground G and the bucket 6 scoops up the soil.

In this example, as in the first example described above, the ground G on which the shovel 100 works has the characteristic that the soil and sand are relatively soft throughout the entire working area. Also, as shown in FIG. 9A, in this example, unlike the first and second examples described above, the ground G on which the shovel 100 works is not flat, and a relatively large convex portion G1 exists in the center of the working area in the front-rear direction. Therefore, the work support unit 302 generates a smooth target trajectory until the timing when the bucket 6 reaches the convex portion G1 in the front-rear direction. As a result, the shovel 100 moves the tip of the bucket 6 on a relatively smooth trajectory 901 corresponding to the target trajectory until the timing when the bucket 6 reaches the convex portion G1 in the front-rear direction, and performs an excavation operation on the shovel 100.

As shown in FIG. 9B, when the bucket 6 reaches the convex portion G1 in the fore-aft direction, the load (reaction force) acting on the bucket 6 suddenly increases due to the influence of the convex portion G1. Therefore, the work support unit 302 updates the target trajectory of the tip of the bucket 6 so as to reduce the load acting on the bucket 6 in accordance with the increase in the load acting on the bucket 6, and causes the excavator 100 to perform an excavation operation so that the tip of the bucket 6 moves along the target trajectory. As a result, the excavator 100 can correct the trajectory 901 of the tip of the bucket 6 to reduce the excavation depth so that the load acting on the bucket 6 decreases after reaching the convex portion G1 in the fore-aft direction.

In this way, in this example, the work support unit 302 can correct the target trajectory of the bucket 6 so that the load acting on the bucket 6 decreases in accordance with an increase in the load acting on the bucket 6 caused by the convex portion G1 of the ground surface G in the work area. Therefore, for example, it is possible to prevent a situation in which the excavation operation of the shovel 100 stagnates due to the presence of the convex portion G1 of the ground surface G in the work area, resulting in a decrease in work efficiency.

In addition, when the characteristics of the soil in the work area change from soft to hard in the forward/backward direction, the work support unit 302 may generate a target trajectory similar to that of this example in accordance with the change in the characteristics of the soil.

<Fourth Example>
FIG. 10 is a diagram showing a fourth example of the trajectory of the working portion of the shovel 100 (trajectories 1001 and 1002).

Figure 10 includes Figures 10A and 10B.

Figure 9A is a diagram showing the trajectory 1001 of the working part (the tip of the bucket 6) during excavation operation of the shovel 100. Figure 9B is a diagram showing the load (reaction force) acting on the attachment AT (bucket 6) corresponding to the trajectory 1001 of the working part of the shovel 100 in time series.

As shown in Figures 10A and 10B, at time t41, the toe of the bucket 6 penetrates into the ground G, and the bucket 6 begins digging into the ground G.

In this example, as in the first and third examples described above, the ground G on which the shovel 100 works has the characteristic that the soil and sand are relatively soft throughout the entire working area. Also, as shown in FIG. 10A, in this example, unlike the first to third examples described above, a rock G2 is buried underground in the center of the working area in the front-to-rear direction. Therefore, the work support unit 302 generates a smooth target trajectory until the bucket 6 reaches the rock G2, and causes the shovel 100 to perform an excavation operation so that the tip of the bucket 6 moves along the target trajectory. As a result, the shovel 100 moves the tip of the bucket 6 along a relatively smooth trajectory 1001 corresponding to the target trajectory until the bucket 6 reaches the rock G2, and performs an excavation operation.

As shown in FIG. 10B, when the bucket 6 reaches the convex portion G1 in the front-rear direction, the load (reaction force) acting on the bucket 6 suddenly increases due to the influence of the convex portion G1, and exceeds the threshold value τth. Therefore, the work support unit 302 updates the target trajectory of the tip of the bucket 6 to a predetermined trajectory for reducing the load, and causes the excavator 100 to perform an excavation operation so that the tip of the bucket 6 moves along the target trajectory. The predetermined trajectory is, for example, a trajectory for lifting the bucket 6 in a direction close to directly above. As a result, after contacting the rock G2, the excavator 100 can lift the bucket 6 on the trajectory 1001 to eliminate the state in which the load acting on the bucket 6 is excessive. In addition, the predetermined trajectory is a trajectory for reducing the load acting on the bucket 6 in accordance with a predetermined condition (two-dot chain line in FIG. 10B). As a result, after the excavator 100 comes into contact with the rock G2, it reduces the excavation depth on the track 1002 while reducing the load acting on the bucket 6 in accordance with the specified conditions, thereby eliminating the condition in which the load acting on the bucket 6 is excessive.

In this way, in this example, the work support unit 302 updates the target trajectory of the bucket 6 to a predetermined trajectory for reducing the load acting on the bucket 6 in response to the occurrence of an excessive load state acting on the bucket 6 due to contact between the bucket 6 and rock G2 underground in the work area. This allows the shovel 100 to move the tip of the bucket 6 on trajectories 1001, 1002 corresponding to the predetermined trajectory, thereby eliminating the excessive load state acting on the bucket 6. Therefore, for example, it is possible to prevent a situation in which the shovel 100 stops or the bucket 6 is damaged due to an excessive load acting on the bucket 6.

[Work progress notification screen]
Next, a specific example of a screen for notifying the user of the progress of work on the work target (the ground surface of the work area) by the shovel 100 will be described with reference to Figs. 11 and 12 .

Figure 11 is a diagram showing an example of a screen (screen 1100) showing the progress of work. Specifically, Figure 11 is a screen showing the progress of work at the start of excavation work by the shovel 100. Figure 12 is a screen showing another example of a screen (screen 1200) showing the progress of work. Specifically, Figure 12 is a screen showing the progress of work after one excavation operation has been performed after the start of excavation work by the shovel 100.

In this example, the screens 1100 and 1200 are displayed on the display device 50A of the shovel 100, but when the shovel 100 is remotely operated, they may be displayed on the display device of the remote operation support device 300. Also, when the shovel 100 is remotely monitored, the screens 1100 and 1200 may be displayed on the display device of the remote monitoring support device.

As shown in FIG. 11, screen 1100 includes a shovel image 1101, a work area image 1102, and a ground image 1103.

The shovel image 1101 is an image that diagrammatically represents the shovel 100. The shovel image 1101 includes a shovel image 1101A that corresponds to the shovel 100 in a side view, and a shovel image 1101B that corresponds to the shovel 100 in a top view.

The work area image 1102 is an image that shows a schematic representation of the work area of the excavator 100.

The work area image 1102 includes a work area image 1102A corresponding to the work area in a side view (side cross section) and a work area image 1102B corresponding to the work area in a top view.

The shovel images 1101A and 1101B are positioned directly opposite the work area images 1102A and 1102B, respectively.

The ground image 1103 is an image that represents the shape of the ground to be worked on before the excavation operation of the shovel 100 begins.

The ground image 1103 includes a ground image 1103A that shows the shape of the ground from a side view (side cross section), and a ground image 1103B that shows the shape of the ground from a top view.

As shown in FIG. 12, screen 1200 includes shovel image 1101, work area image 1102, and ground image 1203.

The ground image 1203 is an image that represents the shape of the ground being worked on after the excavation operation of the shovel 100 has started and after one excavation operation has been completed.

The ground image 1203 includes a ground image 1203A that shows the shape of the ground from a side view (side cross section) and a ground image 1203B that shows the shape of the ground from a top view.

The ground image 1203A includes a completed work image 1203A1 that shows the area that has been excavated by the most recent excavation operation. This allows the user (operator) to check the area that has been excavated by the most recent excavation operation of the excavator 100 in the work area viewed from the side.

The ground image 1203B includes a completed work image 1203B1 that shows the area that has been excavated by the shovel 100. This allows the user (operator) to check the area that has been excavated by repeating the excavation operation of the shovel 100 in the work area viewed from above.

[Processing for generating trajectory of working part of shovel]
Next, a process for generating a trajectory of a working portion of the shovel 100 will be described with reference to FIG.

Figure 13 is a flowchart that shows an example of a process for generating a trajectory for the working part of the shovel 100.

The flowchart in FIG. 13 is executed repeatedly at a predetermined processing cycle, for example, while the excavator 100 is performing a predetermined operation.

As shown in FIG. 13, in step S102, the target trajectory generation unit 302B acquires known input data. The known input data is, for example, setting data for the working area and setting data for the target excavation volume.

When the processing of step S102 is completed, the controller 30 proceeds to step S104.

In step S104, the target trajectory generation unit 302B acquires position information data for the working area of the shovel 100 based on the output data of sensors S1 to S5, etc.

When the processing of step S104 is completed, the controller 30 proceeds to step S106.

In step S106, the target trajectory generation unit 302B acquires the latest output data of the load condition sensor 70.

When the processing of step S106 is completed, the controller 30 proceeds to step S108.

In step S108, the target trajectory generation unit 302B calculates the load state of the attachment AT based on the output data of the load state sensor 70.

When the processing of step S108 is completed, the controller 30 proceeds to step S110.

In step S110, the target trajectory generating unit 302B determines whether the load of the attachment AT is equal to or less than a threshold value τ _th . If the load of the attachment AT is equal to or less than the threshold value τ _th , the target trajectory generating unit 302B proceeds to step S112, and otherwise proceeds to step S122.

In step S112, the target trajectory generating unit 302B uses the learned model LM to estimate the target trajectory of the working part of the shovel 100 and the characteristics of the soil at the location in the working area that is in contact with the working part of the shovel 100. For example, the target trajectory generating unit 302B uses the learned model LM corresponding to the above-mentioned formula (1) to output the target trajectory data θ _t+1:t+H and the soil characteristic parameter ε _t+1 .

When the processing of step S112 is completed, the controller 30 proceeds to step S114.

In step S114, the target trajectory generating unit 302B determines whether the estimated result of the soil characteristics in the working area is within the range of the learned soil characteristics (sediment characteristic parameters) of the trained model LM. If the estimated result of the soil characteristics is within the range of the learned soil characteristics of the trained model LM, the target trajectory generating unit 302B proceeds to step S116, and otherwise proceeds to step S124.

In step S116, the target trajectory generation unit 302B determines whether the target trajectory of the estimation result satisfies the constraint conditions. The constraint conditions are, for example, conditions related to constraints such as the operating range and operating speed of the boom 4, arm 5, and bucket 6 of the attachment AT. If the target trajectory of the estimation result satisfies the constraint conditions, the target trajectory generation unit 302B proceeds to step S118, and otherwise proceeds to step S120.

In step S118, the target trajectory generation unit 302B outputs the target trajectory estimated (generated) using the learned model LM in step S112.

When the processing of step S118 is completed, the controller 30 ends this flowchart.

On the other hand, in step S120, the target trajectory generation unit 302B optimizes the target trajectory estimated (generated) using the learned model LM in step S112 in accordance with the constraint conditions and outputs it.

When the processing of step S120 is completed, the controller 30 ends this flowchart.

In addition, in step S122, the target trajectory generating unit 302B notifies the work progress recording unit 302D of the overload state of the attachment AT. This allows the work progress recording unit 302D to record the location where the overload state of the attachment AT occurred, based on the position of the working part of the excavator 100 acquired in step S104.

When the processing of step S122 is completed, the controller 30 proceeds to step S126.

In addition, in step S124, the target trajectory generating unit 302B notifies the work progress recording unit 302D of the unlearned characteristics of the soil. This allows the work progress recording unit 302D to record the location of the work area that corresponds to the unlearned characteristics of the soil, based on the position of the work part of the excavator 100 acquired in step S104.

When the processing of step S120 is completed, the controller 30 proceeds to step S126.

In step S126, the target trajectory generation unit 302B also outputs the specified trajectory as the target trajectory.

When step S126 is completed, the process of this flowchart ends.

In this way, in this example, the target trajectory generation unit 302B can output a target trajectory for the working part of the shovel 100 using the learned model LM at each predetermined processing cycle during a predetermined operation of the shovel 100. Therefore, the work support unit 302 can cause the shovel 100 to perform an excavation operation while updating the target trajectory during a predetermined operation of the shovel 100 in accordance with the characteristics of the soil and sand in the work area with which the attachment AT (working part) is in contact.

In addition, in this example, the target trajectory generating unit 302B can output a predetermined trajectory as a target trajectory in response to the occurrence of an overload state of the attachment AT. Therefore, the work support unit 302 can reduce the load acting on the attachment AT by causing the shovel 100 to perform an excavation operation so as to move the working part of the shovel 100 along the predetermined trajectory as the target trajectory.

In addition, in this example, the target trajectory generating unit 302B can output a predetermined trajectory as the target trajectory in response to the emergence of unlearned soil characteristics. Therefore, for example, it is possible to prevent a situation in which an inappropriate target trajectory for unlearned soil characteristics is generated by the learned model LM as the target trajectory for the working part of the shovel 100, resulting in an inappropriate predetermined operation of the shovel 100.

[Processing for updating the shape of the work target of the shovel]
Next, a process for updating the shape of the work target (the ground surface of the work area) of the shovel 100 will be described with reference to FIG.

Figure 14 is a flowchart outlining an example of a process for updating work progress.

This flowchart is executed, for example, each time a specified operation of the shovel 100 is completed.

As shown in FIG. 14, in step S202, the work progress recording unit 302D obtains the latest data on the work progress.

When the processing of step S202 is completed, the controller 30 proceeds to step S204.

In step S204, the work progress recording unit 302D acquires data on the trajectory (path) of the work part in the immediately preceding predetermined operation of the excavator 100. For example, the target trajectory generating unit 302B acquires the time series data acquired in the above-mentioned step S104.

When the processing of step S204 is completed, the controller 30 proceeds to step S206.

In step S206, the work progress recording unit 302D acquires data on the notification of unlearned soil characteristics and the notification of an overloaded state of the attachment AT, which were performed during the immediately preceding specified operation of the shovel 100, from the memory device 30B, etc. For example, the work progress recording unit 302D reads data on the notification of unlearned soil characteristics and the notification of an overloaded state of the attachment AT, which were performed by the processing of steps S122 and S124 described above, during the immediately preceding specified operation of the shovel 100, from the memory device 30B, etc.

When the processing of step S206 is completed, the controller 30 proceeds to step S208.

In step S208, the work progress recording unit 302D updates the work progress data based on the data acquired in the processing of steps S204 and S206, assuming the data acquired in the processing of step S202.

When the processing of step S208 is completed, the controller 30 ends the processing of this flowchart.

In this way, the work progress recording unit 302D can update the work progress of the shovel 100 in accordance with the specified operation of the shovel 100 that is realized by the operation control unit 302C based on the target trajectory generated by the target trajectory generating unit 302B.

[Other embodiments]
Next, another embodiment will be described.

The above-described embodiments may be modified or altered as appropriate.

For example, in the above embodiment, when the shovel 100 is remotely operated, the function of the display processing unit 302E may be provided in the remote operation support device 300. This allows a screen related to the generation of a trajectory of the working part of the shovel 100 to be displayed on the display device of the remote operation support device 300. Therefore, a user (operator) of the remote operation support device 300 can use the screen displayed on the display device of the remote operation support device 300 to cause the target trajectory generation unit 302B to generate data representing the trajectory of the working part of the shovel 100.

In addition, in the above-described embodiment and examples of its variations and modifications, when the excavator 100 is remotely operated, some or all of the functions of the trained model storage unit 302A, the target trajectory generation unit 302B, the operation control unit 302C, the work progress recording unit 302D, and the display processing unit 302E may be provided in the remote operation support device 300.

In addition, in the above-described embodiment and examples of variations and modifications thereof, some or all of the functions of the target trajectory generating unit 302B, the operation control unit 302C, the work progress recording unit 302D, and the display processing unit 302E may be transferred to the information processing device 200. This can reduce the processing load on the excavator 100 and the remote operation support device 300 related to the processing related to the generation of the target trajectory of the working part of the excavator 100 and the control of the operation of the excavator 100.

Furthermore, in the above-described embodiment and examples of its variations and modifications, the target trajectory generating unit 302B may output (estimate) only the target trajectory data θ _{t+1:t+H of the shovel 100 without estimating the soil characteristic parameter ε t+1:t+H} . In this case, of the data representing the soil characteristics, the soil characteristic parameter ε _t that directly represents the soil characteristics is omitted, and only the reaction force data f _t−T:t that indirectly represents the soil characteristics is input to the learned model LM.

In the above-described embodiment and its variations and modifications, the sediment characteristic parameters may be given in advance. For example, the sediment characteristic parameters may be input by a user through the input device 52 before starting work or a specified operation, or may be received from outside through the communication device 60.

In addition, in the above-mentioned embodiment and examples of its modifications and changes, the target trajectory generating unit 302B may simply generate a target trajectory of the working part of the shovel 100 only once at the start of a predetermined operation of the shovel 100 or at an early stage after the start. In this case, the target trajectory generating unit 302B generates a target trajectory of the working part until the completion of the predetermined operation of the shovel 100. Then, the operation control unit 302C executes the predetermined operation of the shovel 100 until completion so that the working part of the shovel 100 moves along one target trajectory generated by the target trajectory generating unit 302B. For example, after the start of the excavation operation of the shovel 100, the target trajectory generating unit 302B generates a target trajectory of the tip of the bucket 6 of the shovel 100 based on the reaction force data when the bucket 6 penetrates into the soil of the work target. In addition, the target trajectory generating unit 302B may generate a target trajectory of the working part of the shovel 100 based on a soil characteristic parameter ε given in advance at the start of the predetermined operation of the shovel 100. Furthermore, if the soil and sand characteristic parameter ε is given in advance, the target trajectory generating unit 302B may generate a target trajectory for the work part for the initial multiple operations at the start of work, or for the multiple operations until the end of work.

In addition, in the above-described embodiment and examples of variations and modifications thereof, the target trajectory generating unit 302B may generate data on the target trajectory of the working part of the shovel 100 that is adapted to the characteristics of the soil to be worked on by applying any known method instead of the learned model LM. For example, the target trajectory generating unit 302B may generate data on the target trajectory of the working part of the shovel 100 by MPC (Model Predictive Control) based on data on the characteristics of the soil. The target trajectory generating unit 302B may also generate data on the target trajectory of the working part of the shovel 100 by optimizing a predetermined reference trajectory of the working part of the shovel 100 based on data on the characteristics of the soil that is given in advance.

[Action]
Next, the operations of the work machine, work support system, information processing device, and program according to the above-described embodiment will be described.

In this embodiment, the work machine includes a generation unit. The work machine is, for example, the shovel 100 described above. The generation unit is, for example, the target trajectory generation unit 302B described above. Specifically, the generation unit generates data representing the trajectory of the working part of the work machine based on data related to the characteristics of the soil and sand to be worked on during a specified operation of the work machine. The specified operation is, for example, the excavation operation or compaction operation of the shovel 100 described above. The work object is, for example, the ground surface of the work area at the work site of the shovel 100.

This allows the work machine to generate a trajectory for the working part of the work machine that matches the characteristics of the soil being worked on.

In addition, in this embodiment, the generation unit may use a trained model that has undergone supervised learning using data collected during a specified operation of the work machine by the operation of a specified operator, and output data representing the trajectory of the work area using data related to the characteristics of the soil to be worked on as input. The specified operator is, for example, the above-mentioned expert. The trained model is, for example, the above-mentioned trained model LM.

This allows the work machine to use the learned model to realize, for example, a trajectory of the work part that imitates the operation of an expert. This allows the work machine to improve its work efficiency.

In addition, in this embodiment, the generation unit may acquire data on reaction forces acting on the work area from the work target as data on the characteristics of the soil and sand on the work target, and during a specified operation of the work machine, sequentially update the data representing the trajectory of the work area based on the time-series data on reaction forces.

This allows the work machine to perform a specified operation while appropriately updating the trajectory of the working part in accordance with the reaction force acting on the working part, which correlates with the characteristics of the soil being worked on. Therefore, the work machine can realize a more appropriate trajectory of the working part by taking into account changes in the characteristics of the soil within the working area. This allows the work machine to further improve its work efficiency.

In this embodiment, the work machine may also be equipped with an estimation unit. Specifically, the estimation unit acquires data on the reaction force acting on the work part from the work object as data on the characteristics of the soil on the work object, and estimates the characteristics of the soil on the work object based on the time-series data on the reaction force. The generation unit may then generate data representing the trajectory of the work part based on the soil characteristics estimated by the estimation unit during a specified operation of the work machine.

This allows the work machine to estimate the characteristics of the soil from the reaction force acting on the working part, enabling it to realize a trajectory for the working part that matches the characteristics of the soil in the working area.

Furthermore, in this embodiment, the generation unit may generate data representing the trajectory of the working part based on time-series data relating to the reaction force when the reaction force is relatively small compared to a predetermined criterion during a predetermined operation of the work machine. On the other hand, the generation unit may generate data representing the trajectory of the working part that is predefined so that the reaction force decreases when the reaction force is relatively large compared to the predetermined criterion during a predetermined operation of the work machine. The predetermined criterion is, for example, the threshold value τ _th described above.

As a result, when the work machine is in an overload state where the reaction force acting on the working part exceeds a predetermined standard, the trajectory of the working part can be corrected so that the reaction force acting on the working part is reduced. Therefore, for example, it is possible to prevent a situation in which the work machine stops or the working part is damaged due to an overload state of the reaction force acting on the working part.

In this embodiment, the work machine may also include a control unit. The control unit is, for example, the operation control unit 302C described above. Specifically, the control unit controls the operation of the work machine so that the working part moves along a trajectory corresponding to the data generated by the generation unit.

This allows the work machine to move the working area along a trajectory generated according to the characteristics of the soil and sand, either independently of the operator's operation or by assisting the operator's operation.

In this embodiment, the work machine may also include a display unit. The display unit is, for example, the display device 50A described above. Specifically, the display unit displays the progress of work in the area to be worked on by the work machine. The display unit may then update the progress of work in the area to be worked on in response to the operation of the work machine by the control unit.

This allows the work machine to inform the user (operator) in the cabin and surrounding workers of the progress of work in the target work area in accordance with the work machine's specified actions.

In addition, in this embodiment, the display unit may identify and display at least one of the locations within the area of the work target of the work machine where the reaction force acting from the work target on the work part becomes relatively large with respect to a predetermined standard, and the locations where the characteristics of the soil in the work target estimated based on the data related to the reaction force deviate from a predetermined range. The predetermined range is, for example, the range of the soil characteristic parameter ε that has been learned by the learned model LM.

This allows the work machine to inform the user (operator) in the cabin and surrounding workers of locations within the work area where an overload condition has occurred, where the reaction force acting on the work part exceeds a specified standard. The work machine can also inform the user (operator) in the cabin and surrounding workers of locations within the work area where the characteristics of the soil and sand being worked on deviate from the expected range.

In addition, in this embodiment, the information processing device performs supervised learning of a learning model based on data collected during a specified operation of the work machine operated by a specified operator. Then, as a result of the supervised learning, the information processing device may generate a learned model that takes as input data related to the characteristics of the soil and sand that is the target of the work machine's work, and outputs data representing the trajectory of the work part during the specified operation of the work machine. The information processing device is, for example, the above-mentioned information processing device 200. The specified operator is, for example, the above-mentioned expert. The learned model is, for example, the learned model LM.

This allows the information processing device to generate a trained model that can generate a target trajectory for the work machine that matches the characteristics of the soil and sand in the work area.

In addition, in this embodiment, the work support system may include a first transmission unit, a generation unit, and a second transmission unit. The work support system is, for example, the work support system SYS described above. The first transmission unit is, for example, the communication device 60 described above. The generation unit is, for example, a functional unit equivalent to the target trajectory generation unit 302B transferred to the information processing device 200 described above. The second transmission unit is, for example, the communication interface 206 described above. Specifically, the first transmission unit is provided in the work machine and transmits data regarding the characteristics of the soil and sand that is the work target of the work machine to the information processing device. The information processing device is, for example, the information processing device 200 described above. The generation unit is provided in the information processing device and generates data representing the trajectory of the work part based on the data regarding the characteristics of the soil and sand during a specified operation of the work machine. The second transmission unit is provided in the information processing device and transmits to the work machine a command to control the work machine so that the work part moves along the data generated by the generation unit or a trajectory corresponding to the data generated by the generation unit.

This allows the work assistance system to generate a trajectory for the work machine in accordance with the characteristics of the soil and sand in the work area of the work machine using an information processing device. The work assistance system can also reduce the processing load on the work machine.

In addition, in this embodiment, the program causes the information processing device to execute a generation step. The information processing device is, for example, the controller 30 or the information processing device 200 described above. The generation step is, for example, steps S102 to S122 described above. Specifically, the generation step generates data representing the trajectory of the working part of the work machine based on data related to the characteristics of the soil and sand that is the target of the work machine's work during a specified operation of the work machine.

As a result, by applying this program, the information processing device can generate a trajectory for the working part of the work machine in accordance with the characteristics of the soil and sand that the work machine is working on.

Although the embodiments have been described in detail above, the present disclosure is not limited to such specific embodiments, and various modifications and variations are possible within the scope of the gist of the invention as described in the claims.

1 Lower traveling body 3 Upper rotating body 4 Boom 5 Arm 6 Bucket 30 Controller 31 Hydraulic control valve 32 Shuttle valve 33 Hydraulic control valve 50 Output device 50A Display device 52 Input device 60 Communication device 70 Load state sensor 100 Shovel 150 Support device 200 Information processing device 300 Remote operation support device 301 Operation log providing unit 301A Operation log recording unit 301B Operation log storage unit 301C Operation log transmission unit 302 Work support unit 302A Learned model storage unit 302B Target trajectory generation unit 302C Operation control unit 302D Work progress status recording unit 302E Display processing unit 2001 Operation log acquisition unit 2002 Operation log storage unit 2003 Teacher data generation unit 2004 Machine learning unit 2005 Learned model storage unit 2006 Distribution unit AT Attachment HA Hydraulic actuator LM Learned models S1 to S5 Sensor SYS Work Support System

Claims (11)

a generation unit that generates data representing a trajectory of a working portion of the work machine based on data relating to characteristics of soil and sand as a work target during a predetermined operation of the work machine;
Working machinery. The generation unit uses a trained model that has been subjected to supervised learning using data collected during the specified operation of the work machine by the operation of a specified operator, and inputs data related to the characteristics of the soil to be worked on, and outputs data representing the trajectory of the work area.
2. The work machine of claim 1. The generation unit acquires data on a reaction force acting on the work part from the work object as data on characteristics of the soil of the work object, and sequentially updates data representing a trajectory of the work part based on the time-series data on the reaction force during the specified operation of the work machine.
A work machine according to claim 1 or 2. An estimation unit that acquires data on the reaction force acting on the work part from the work object as data on the characteristics of the soil of the work object, and estimates the characteristics of the soil of the work object based on the time-series data on the reaction force,
the generation unit generates data representing a trajectory of the work portion based on the characteristics of soil and sand estimated by the estimation unit during the specified operation of the work machine.
4. A work machine according to claim 3. the generation unit generates data representing a trajectory of the working part based on time-series data relating to the reaction force when the reaction force is relatively small with respect to a predetermined standard during the specified operation of the work machine, and generates data representing a trajectory of the working part that is predefined so that the reaction force is reduced when the reaction force is relatively large with respect to the predetermined standard.
4. The work machine according to claim 3. a control unit that controls an operation of a work machine so that the working part moves along a trajectory corresponding to the data generated by the generation unit;
A work machine according to claim 1 or 2. a display unit that displays a progress status of the work in the work target area,
The display unit updates the progress of the work in the area in response to the operation of the work machine by the control unit.
7. A work machine according to claim 6. The display unit identifies and displays at least one of a location in the area where a reaction force acting from the work object to the work part becomes relatively large with respect to a predetermined standard, and a location where a characteristic of the soil of the work object estimated based on data related to the reaction force deviates from a predetermined range.
8. A work machine according to claim 7. A learning model is subjected to supervised learning based on data collected during a predetermined operation of the work machine operated by a predetermined operator, and a learned model is generated that receives data on the characteristics of the soil and sand that is the target of the work machine as an input and outputs data representing the trajectory of a working part of the work machine during the predetermined operation.
Information processing device. a first transmission unit provided in the work machine and configured to transmit data relating to characteristics of the soil and sand that is the object of work by the work machine to an information processing device;
a generation unit provided in the information processing device and configured to generate data representing a trajectory of a working portion of the work machine based on data relating to characteristics of the soil and sand during a predetermined operation of the work machine;
a second transmission unit provided in the information processing device and configured to transmit to the work machine a command for controlling the work machine so that the working part moves along the data generated by the generation unit or a trajectory corresponding to the data generated by the generation unit,
Work support system. In the information processing device,
executing a generating step of generating data representing a trajectory of a working portion of the work machine based on data relating to characteristics of soil and sand that is a target of work by the work machine during a predetermined operation of the work machine;
program.

Images