JP7828607B2 - Control devices for industrial vehicles, control systems for industrial vehicles, and programs for industrial vehicle control devices. - Google Patents

Description

This invention relates to a control device for industrial vehicles, a control system for industrial vehicles, and a program for a control device for industrial vehicles.

As a control device for industrial vehicles, for example, the one described in Patent Document 1 is known. The control device for industrial vehicles described in Patent Document 1 estimates the working state of the industrial vehicle based on operation information for the industrial vehicle, and controls the industrial vehicle based on the estimated working state.

Japanese Patent Publication No. 2019-189435

To estimate the work state of a control device, a work state estimation model is constructed that sets estimation indicators such as transition conditions and transition thresholds for each work state. However, designing estimation indicators for work state estimation presents problems such as the difficulty of the design work, the difficulty in improving accuracy, and the enormous amount of effort required for design.

The objective of this invention is to provide an industrial vehicle control device, an industrial vehicle control system, and a program for an industrial vehicle control device that can accurately acquire estimation indicators for estimating the working state of an industrial vehicle with minimal effort.

One aspect of the present invention relates to a control device for an industrial vehicle, which is a control device for estimating the working state of an industrial vehicle. It includes a working state estimation unit that uses machine learning to estimate the working state of the industrial vehicle. The working state estimation unit performs machine learning based on input of operation information related to the operating state of the industrial vehicle and input of correct data on the working state.

The control device for industrial vehicles has a work state estimation unit that uses machine learning to estimate the work state of the industrial vehicle. Therefore, the control device can design estimation indicators for estimating the work state of the industrial vehicle through machine learning. Here, the work state estimation unit performs machine learning based on input of operation information regarding the operation state of the industrial vehicle and input of ground truth data for the work state. In this way, the work state estimation unit can perform machine learning based on input of operation information actually performed in the past and ground truth data indicating what work state resulted from that operation information. As a result, the control device can obtain estimation indicators for estimating the work state of the industrial vehicle simply by performing machine learning using past operation information and ground truth data. Furthermore, since these estimation indicators are based on actual past data, they enable accurate estimation of the work state. Therefore, estimation indicators for estimating the work state of industrial vehicles can be obtained accurately with minimal effort.

The work state estimation unit may receive current operation information as input and output the current work state based on the learning results. This allows the work state estimation unit to easily estimate the current work state simply by inputting current operation information.

The control device for industrial vehicles may further include a cargo state estimation unit that outputs a cargo state related to the condition of the cargo handled by the industrial vehicle based on the work state output by the work state estimation unit, and a work state correction unit that corrects the work state based on the work state output by the work state estimation unit and the cargo state output by the cargo state estimation unit. In this case, the control device can improve the accuracy of work state estimation by making corrections that take into account the cargo state of the industrial vehicle.

The operation information may include at least one of the following: accelerator input, tire angle, lift input, reach input, and tilt input. These parameters reflect the operator's intentions in industrial vehicles. The work state estimation unit can perform appropriate machine learning by using these parameters as operation information.

The work state estimation unit may use LSTM as the machine learning model and perform machine learning using operation information acquired in time series as training data. When performing machine learning using operation information acquired in time series, LSTM can perform learning considering not only the most recent data but also past data. Therefore, the work state estimation unit can obtain more accurate estimation indicators.

One aspect of the present invention relates to an industrial vehicle control system comprising the above-described industrial vehicle control device.

A program for a control device for an industrial vehicle according to one aspect of the present invention is used in the above-described control device for an industrial vehicle.

The control systems and control devices for these industrial vehicles can achieve the same functions and effects as the control devices for industrial vehicles described above.

According to the present invention, it is possible to provide an industrial vehicle control device, an industrial vehicle control system, and a program for an industrial vehicle control device that can acquire an industrial vehicle operation state estimation model with low man-hours and high accuracy.

This is a block diagram showing a driver assistance system according to an embodiment of the present invention. (a) is a perspective view showing how the camera unit is attached to the forklift, and (b) is a schematic diagram illustrating the angle of the camera unit. This is a diagram illustrating the working state of a forklift. This is a block diagram of the work status acquisition unit. This figure shows the machine learning process of the work state estimation unit. This is a flowchart showing the processing steps of the driver assistance system. This graph illustrates the effects of the cargo condition estimation unit and the work condition correction unit. This graph shows the experimental results of the control device.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the drawings. In the drawings, identical or equivalent elements are denoted by the same reference numerals, and redundant descriptions are omitted.

Figure 1 is a block diagram showing a driver assistance system 100 (industrial vehicle control system) including a control device 20 according to an embodiment of the present invention. The driver assistance system 100 is a system for remotely controlling an industrial vehicle. As shown in Figure 1, the driver assistance system 100 comprises a forklift 1 (industrial vehicle) and a remote control device 2.

The forklift 1 comprises a driving control unit 11 and multiple imaging units 12. The driving control unit 11 receives command signals from the remote control device 2 and performs driving and steering control based on these command signals. The multiple imaging units 12 are installed at various points on the forklift 1 and capture images of the surrounding environment. The imaging units 12 acquire the captured images as support information used for work assistance and transmit them to the display control unit 22 (described later). An example of the mounting positions of the multiple imaging units 12 is shown in Figure 2(a). The imaging units 12 are installed at the front end, widthwise ends, ceiling, etc., of the forklift 1's body. Note that, as shown in Figure 2(b), when XYZ coordinates are set, the imaging units 12 at each location may be installed at an angle around the X, Y, and Z axes. In Figure 2(a), eight imaging units 12 are installed, each acquiring images of a different location.

As shown in Figure 1, the remote control device 2 comprises a storage unit 15, an operation unit 16, a display unit 17, an operation information acquisition unit 18, and a control device 20. The storage unit 15 is a device for storing various types of information. The operation unit 16 is a user interface for an operator to input operations for remotely controlling the forklift 1. The display unit 17 is a user interface for outputting video. The display unit 17 has a first area D1, a second area D2, and a third area D3, each capable of outputting different video.

The operation information acquisition unit 18 acquires operation information when the operator is operating the target device (in this case, the operation unit 16). The operation information acquisition unit 18 is configured, for example, by a sensor provided on the operation lever of the operation unit 16, or by means of detecting the operation content based on a signal indicating the operation content of the operation unit 16.

The control device 20 is a control unit that controls the entire remote control device 2. The control device 20 includes an ECU (Electronic Control Unit) that comprehensively manages the remote control device 2. The ECU is an electronic control unit comprising a CPU (Central Processing Unit), ROM (Read Only Memory), RAM (Random Access Memory), CAN (Controller Area Network), communication circuits, etc. The ECU, for example, implements various functions by loading a program stored in ROM into RAM and executing the program loaded into RAM using the CPU. The control device 20 includes an operation command unit 21, a display control unit 22, a work status acquisition unit 23, and a viewpoint information acquisition unit 26.

The operation command unit 21 is a unit that generates command signals based on the operations input by the operation unit 16 and transmits them to the operation control unit 11.

The display control unit 22 is a unit that controls the display content of the display unit 17. The display control unit 22 displays information on the display unit 17 to support the operator's remote operation. The display control unit 22 controls the display content of the first area D1, second area D2, and third area D3 of the display unit 17 using information from the database in the storage unit 15.

The display control unit 22 selects the image to be displayed on the display unit 17 based on the viewpoint information acquired by the viewpoint information acquisition unit 26. The first area D1 and the second area D2 are large-screen areas that display a specific image in a larger size, and the image from the selected camera unit 12 from among the images from multiple camera units 12 is displayed. The third area D3 corresponds to a small-screen area that displays multiple images in a smaller size, and displays images from all camera units 12 on the forklift 1 as environmental information for surrounding confirmation.

For example, Figure 3(a) is a table defining the working states of forklift 8. Here, as an example of working states, seven states related to the movement of forklift 3 and the loading/unloading of cargo—"Stop," "Move forward," "Approach," "Adjust heading," "Load/Unload," "Retreat," and "Move reverse"—are divided into states with and without cargo, resulting in a total of 14 working states. The movement of forklift 3 corresponds to "Stop," "Move forward," "Approach," "Retreat," and "Move reverse," while the loading/unloading of cargo corresponds to "Adjust heading" and "Load/Unload." The definitions and number of each work state are not limited to those above and can be changed as appropriate. Alternatively, work states may be defined only in relation to the movement of forklift 3 (industrial vehicle). Figure 3(b) is a schematic diagram showing the various work states when forklift 1 loads cargo from shelf SF and unloads cargo. In the database of the memory unit 15, each work state is linked to the camera unit 12, which can capture images of the parts that need to be checked in that work state. Therefore, the display control unit 22 can display images of areas requiring particular attention in the first area D1 and the second area D2 on a large screen, according to the working status of the forklift 1 being operated by the operator. Note that the images displayed on the display unit 17 under the control of the display control unit 22 for driver assistance may be referred to as "driver assistance images."

Regarding the appropriate timing for switching the driver assistance video, there are individual differences among operators. Furthermore, when the work state performed by forklift 1 changes, the video to be displayed on the display unit 17 changes. In light of these circumstances, the work state acquisition unit 23 and the viewpoint information acquisition unit 26 adapt the driver assistance video to the individual operator and perform processing corresponding to the state transition of the work state.

The work status acquisition unit 23 acquires the work status being performed by the forklift 1. The work status acquisition unit 23 acquires the work status based on the operation information acquired by the operation information acquisition unit 18. The work status acquisition unit 23 acquires the work status using a work status estimation model that sets estimation indicators such as transition conditions and transition thresholds for transitioning to each work status. The work status acquisition unit 23 may acquire the work status estimation model stored in the storage unit 15. Details of the work status acquisition unit 23 will be described later. The work status acquisition unit 23 transmits the acquired work status to the viewpoint information acquisition unit 26.

The viewpoint information acquisition unit 26 acquires the operator's viewpoint based on the work status acquired by the work status acquisition unit 23. Here, the storage unit 15 has a database that links the work status of the forklift 1 with viewpoint information based on the operator's gaze. Therefore, the viewpoint information acquisition unit 26 acquires viewpoint information corresponding to the work status by comparing the work status of the forklift 1 with the database. The viewpoint information acquisition unit 26 transmits the acquired viewpoint information to the display control unit 22. As a result, the display control unit 22 controls the image displayed on the display unit 17 based on the viewpoint information, enabling it to display the optimal image for the work status of the forklift 1 and the individual operator.

Next, the detailed configuration of the work status acquisition unit 23 will be described with reference to Figure 4. Figure 4 is a block diagram showing the configuration of the work status acquisition unit 23. As shown in Figure 4, the work status acquisition unit 23 comprises a work status estimation unit 30, a cargo status estimation unit 31, and a work status correction unit 32.

The work state estimation unit 30 estimates the work state of the forklift 1 using machine learning. The work state estimation unit 30 receives current operation information u(t) as input and outputs the current work state x(t) based on the learning results. The work state estimation unit 30 has a machine learning model M1.

The classifications "1" to "14" shown in Figure 3(a) are used to represent the working state. Operational information includes at least one of the following: accelerator operation amount, tire angle, lift operation amount, reach operation amount, and tilt operation amount. Accelerator operation amount is a parameter indicating the amount of accelerator operation on the forklift 1; a larger accelerator operation amount indicates a faster forklift 1 speed. Tire angle is a parameter indicating the turning angle of the forklift 1's tires; a larger tire angle indicates a larger turning radius. Lift operation amount is a parameter indicating the amount of operation to lift the forks of the forklift 1; a larger lift operation amount indicates a greater fork lift. Reach operation amount is a parameter indicating the amount of operation to extend the forks of the forklift 1 forward; a larger reach operation amount means a greater forward movement of the forks. Tilt operation amount is a parameter indicating the amount of operation to tilt the forks of the forklift 1; a larger tilt operation amount means a greater tilt of the forks.

The work state estimation unit 30 estimates and outputs the current work state x(t) by comparing the input current operation information u(t) with a work state estimation model that has been set with estimation indicators such as transition conditions and transition thresholds for transitioning to each work state. The work state estimation model has been set which parameters of the above-mentioned operation information need to be increased (decreased) and by how much for a transition to one work state to occur. For example, as shown in Figure 3(b), in "Work State 4" "Adjust heading," the forklift 1 is in a state where it is making a large turn, and in "Work State 5" "Load," the forklift 1 is moving slowly. Therefore, the work state estimation unit 30 can estimate that a transition from "Work State 4" to "Work State 5" has occurred when the accelerator operation amount is large and the tire angle is large, and each parameter falls below a predetermined threshold. In such a work state estimation model, machine learning is used to set the optimal estimation indicators for the operator based on the operator's past driving performance. Furthermore, individual work state estimation models may be created for each operator, or a work state estimation model not limited to a specific operator may be created. The work state estimation models are stored in the storage unit 15, and the work state estimation unit 30 retrieves the appropriate work state estimation model corresponding to the operator from the storage unit 15 at the necessary timing.

Figure 5 is a block diagram showing the operation state estimation unit 30 during learning. As shown in Figure 5, the operation state estimation unit 30 performs machine learning by inputting operation information related to the operation state of the forklift 1 and correct data on the operation state. The machine learning process shown in Figure 5 may be performed in advance, before the actual remote operation of the forklift 1 takes place. Pre-prepared data is used as operation information and correct data. For example, the forklift 1 is actually operated in a laboratory, and data is acquired by linking the operation information at a certain time with the actual operation state at that time. The actual operation state at this time becomes the correct data.

The work state estimation unit 30 may use LSTM (Long Short Term Memory) as the machine learning model M1. In this case, the work state estimation unit 30 may perform machine learning using operation information acquired in time series as training data. The operation information acquired in time series consists, for example, of a data set of "operation information u(t) and correct work state y(t)" acquired at predetermined intervals from "time 0" to "time T". The work state estimation unit 30 may also use RNN (Recurrent Neural Network) as the machine learning model M1, which is capable of handling operation information acquired in time series.

Returning to Figure 4, the cargo state estimation unit 31 outputs a cargo state g(t) related to the state of the cargo handled by the forklift 1, based on the work state x(t) output by the work state estimation unit 30. The cargo state estimation unit 31 has a pre-created cargo state estimation model (state transition model) M2. The cargo state estimation unit 31 obtains the cargo state estimation model M2 from the storage unit 15. The cargo state estimation unit 31 estimates the cargo state g(t) by comparing the estimated work state x(t) with the cargo state estimation model M2. The cargo state g(t) indicates either "NL: No Load (no cargo)" or "L: Load (cargo present)". The cargo state estimation unit 31 outputs the estimated cargo state g(t) to the work state correction unit 32.

The cargo state estimation model M2 prohibits transitions in cargo states other than the specified work state. For example, in the example in Figure 3, in "Work State 5," forklift 1 approaches shelf SF without cargo, and after receiving the cargo, transitions to "Work State 6," the preparation for travel. In this case, the cargo state estimation model M2 allows the transition from "NL: No Cargo" to "L: Cargo Present" when transitioning from "Work State 5" to "Work State 6," and prohibits any other transitions. Similarly, in "Work State 12," forklift 1 approaches shelf SF with cargo, and after unloading the cargo onto shelf SF, transitions to "Work State 13," the preparation for travel. In this case, the cargo state estimation model M2 allows the transition from "L: Cargo Present" to "NL: No Cargo" when transitioning from "Work State 12" to "Work State 13," and prohibits any other transitions.

The work state correction unit 32 corrects the work state based on the work state x(t) output by the work state estimation unit 30 and the luggage state g(t) output by the luggage state estimation unit 31, and outputs the corrected work state s(t). The work state correction unit 32 determines whether the work state x(t) output by the work state estimation unit 30 is a work state with luggage or a work state without luggage. Next, the work state correction unit 32 compares the presence or absence of luggage in the work state x(t) with the luggage state g(t) output by the luggage state estimation unit 31. If the presence or absence of luggage in both matches, the work state correction unit 32 sets the corrected work state s(t) to be the same as the work state x(t). On the other hand, if the presence or absence of luggage in both does not match, the work state correction unit 32 corrects the work state x(t) to match the luggage state g(t). For example, if the work state estimation unit 30 estimates that there has been a transition from a work state with cargo (t-1) to a work state without cargo (t), while the cargo state estimation unit 31 estimates that there has been no transition between cargo state g(t-1) with cargo and cargo state g(t) with cargo, the work state correction unit 32 corrects the work state x(t) without cargo to a work state s(t) with cargo. Note that in the table in Figure 3(a), incorrect estimations are likely to occur within the same operation category. For example, in the operation "Adjust heading," it is easy to confuse "work state 4" and "work state 11." Therefore, the work state correction unit 32 corrects the presence or absence of cargo within the same operation category. Consequently, if "work state 4" is incorrect, the work state correction unit 32 corrects it to "work state 1," which is in the same operation category as "work state 4." If "Working State 11" is incorrect, the working state correction unit 32 corrects it to "Working State 4," which is in the same operation category as "Working State 11."

Next, with reference to Figure 6, an example of the processing content showing the driving support method by the control device 20 will be described. The processing shown in Figure 6 is performed when the driving support video is displayed on the display unit 17 and the operator is remotely operating the forklift 1. As shown in Figure 6, the operation information acquisition unit 18 acquires operation information from the operator (step S10). Next, the work state estimation unit 30 estimates the work state based on the operation information acquired in step S (step S20). Next, the load state estimation unit 31 acquires the load state based on the work state estimated in step S20 (step S30). Next, the work state correction unit 32 corrects the work state based on the work state estimated in step S20 and the load state estimated in step S30 (step S40). Next, the viewpoint information acquisition unit 50 acquires viewpoint information based on the work state corrected in step S50 (step S50). Next, the display control unit 22 selects the driving support video to be displayed on the display unit 17 based on the viewpoint information acquired in step S50 (step S60).

Next, the operation and effects of the control device 20 according to this embodiment will be described.

The control device 20 has a work state estimation unit 30 that estimates the work state of the forklift 1 using machine learning. Therefore, the control device 20 can design estimation indicators for estimating the work state of the forklift 1 through machine learning. Here, the work state estimation unit 30 performs machine learning based on input of operation information regarding the operation state of the forklift 1 and input of correct data on the work state. In this way, the work state estimation unit 30 can perform machine learning based on input of operation information actually performed in the past and correct data indicating what work state resulted from that operation information. As a result, the control device 20 can obtain estimation indicators for estimating the work state of the forklift 1 simply by performing machine learning using past operation information and correct data. Furthermore, since these estimation indicators are based on actual past data, they enable accurate estimation of the work state. Therefore, estimation indicators for estimating the work state of the forklift 1 can be obtained accurately with minimal effort.

The work state estimation unit 30 may receive current operation information as input and output the current work state based on the learning results. This allows the work state estimation unit 30 to easily estimate the current work state simply by inputting current operation information.

The control device 20 may further include a load condition estimation unit 31 that outputs a load condition related to the state of the load handled by the forklift 1 based on the work condition output by the work condition estimation unit 30, and a work condition correction unit 32 that corrects the work condition based on the work condition output by the work condition estimation unit 30 and the load condition output by the load condition estimation unit 31. In this case, the control device 20 can improve the accuracy of work condition estimation by correcting the load condition of the forklift 1.

Referring to Figure 7, the effects of the cargo status estimation unit 31 and the work status correction unit 32 will be explained. Figure 7(a) is a graph showing the estimated work status results estimated by the work status estimation unit 30, when operation information at a certain time is shown chronologically on the horizontal axis. Figure 7(b) is a graph showing the estimated results when the work status estimated by the work status estimation unit 30 is corrected by the work status correction unit 32. The dashed lines in Figures 7(a) and 7(b) represent the presence or absence of cargo. If the dashed line is in the upper section, it indicates a "cargo present" state, and if it is in the lower section, it indicates a "cargo absent" state.

For example, in Figure 7(a), it is estimated that the state transitioned from "working state 4," where the forks are aligned without a load, to "working state 11," where the forks are aligned with a load, and then to "working state 5," which is the loading/unloading state with a load. Thus, as shown by "FD" in Figure 7(a), the location where the estimation result fluctuates sharply indicates that the working state estimation unit 30 initially estimated an incorrect working state, and then subsequently estimated the correct working state.

In contrast, the cargo state estimation unit 31 prohibits the transition from "NL: No cargo" to "L: Cargo present" when transitioning from "Work state 4" to "Work state 11". Therefore, the cargo state estimation unit 31 outputs "NL: No cargo" as the cargo state to the work state correction unit 32, based on the work state estimation unit 30's estimation result of "Work state 11" (where cargo is present). As a result, the work state correction unit 32 corrects "Work state 11" (where cargo is present) to "Work state 4" (where cargo is absent) to match the estimation result of the cargo state estimation unit 31. This allows the system to estimate that the transition from "Work state 4" to "Work state 5" occurred at the correct timing, i.e., the actual timing of the transition from "Cargo present" to "Cargo absent," without going through "Work state 11," as shown in Figure 7(b). This suppresses the occurrence of incorrect work states, such as "FD" in Figure 7(a), as shown in Figure 7(b).

The operation information may include at least one of the following: accelerator input, tire angle, lift input, reach input, and tilt input. These parameters reflect the operator's intentions in the forklift 1. The work state estimation unit 30 can perform appropriate machine learning by using these parameters as operation information.

The work state estimation unit 30 may use LSTM as the machine learning model M1 and perform machine learning using operation information acquired in time series as training data. When performing machine learning using operation information acquired in time series, LSTM can perform learning considering not only the most recent data but also past data. Therefore, the work state estimation unit 30 can obtain a more accurate estimation index.

The driving support system 100 (industrial vehicle control system) according to this embodiment includes the industrial vehicle control device 1 described above.

The program for the industrial vehicle control device according to this embodiment is used in the industrial vehicle control device 20 described above.

Specifically, the program for the industrial vehicle's control system instructs the computer system to execute a work state estimation step that uses machine learning to estimate the industrial vehicle's working state. In the work state estimation step, machine learning is performed by inputting operational information regarding the industrial vehicle's operating state and correct data on the working state.

The control systems for these industrial vehicles, and the programs for the industrial vehicle control devices 20, can achieve the same functions and effects as the industrial vehicle control devices 20 described above.

Referring to Figure 8, the experimental results of estimating the work state using the control device 20 according to this embodiment will be described. Here, the percentage (accuracy rate) in which the actual work state and the estimated result matched was calculated for a specific work pattern. In Figure 8, the solid line graph G1 shows the estimation results, and the dashed line graph G2 shows the actual work state. In the graphs shown in Figure 8, where graphs G1 and G2 overlap, the estimation results match the actual work state, and where graphs G1 and G2 do not overlap, the estimation results do not match the actual work state. Multiple operators were prepared, 44 work data sets were acquired, and the average accuracy rate for all 44 sets was calculated and evaluated. Compared to the estimation results using a work state model designed without machine learning, the accuracy rate of the estimation results of the control device 20 according to this embodiment improved by approximately 10%.

Although several preferred embodiments of the present invention have been described above, the present invention is not limited to the embodiments described above.

In the above-described embodiment, the driver assistance system supported the operator's work during remote operation; however, it may also provide assistance when the industrial vehicle is operated by a human. Furthermore, it may provide assistance when the operator is performing a simulated operation of the industrial vehicle.

Industrial vehicles are not limited to forklifts; towing tractors, skid steer loaders, and other types of vehicles may also be used.

[Form 1]
A control device for estimating the working state of an industrial vehicle,
It has a work state estimation unit that estimates the work state of the industrial vehicle using machine learning,
The aforementioned work state estimation unit is a control device for an industrial vehicle that performs machine learning by inputting operation information relating to the operating state of the industrial vehicle and correct data of the work state.

[Form 2]
The control device for an industrial vehicle according to Embodiment 1, wherein the work state estimation unit receives the current operation information as input and outputs the current work state based on the learning results.

[Form 3]
A cargo condition estimation unit outputs a cargo condition relating to the condition of the cargo handled by the industrial vehicle, based on the work condition output by the work condition estimation unit.
A control device for an industrial vehicle according to embodiment 1 or 2, further comprising: a work state correction unit that corrects the work state based on the work state output by the work state estimation unit and the cargo state output by the cargo state estimation unit.

[Form 4]
The control device for an industrial vehicle according to any one of embodiments 1 to 3, wherein the operation information includes at least one of the accelerator operation amount, tire angle, lift operation amount, reach operation amount, and tilt operation amount.

[Form 5]
The control device for an industrial vehicle according to any one of the embodiments 1 to 4, wherein the work state estimation unit uses LSTM as a machine learning model and performs machine learning using the operation information acquired in time series as training data.

[Form 6]
A control system for an industrial vehicle having a control device for an industrial vehicle as described in any one of the embodiments 1 to 5.

[Form 7]
A program for an industrial vehicle control device used in an industrial vehicle control device according to any one of claims 1 to 5.

1…Forklift, 30…Working condition estimation unit, 31…Load condition estimation unit, 32…Working condition correction unit, 100…Driving support system (industrial vehicle control system).

Claims (6)

A control device for estimating the working state of an industrial vehicle,
A work state estimation unit that estimates the work state of the industrial vehicle using machine learning ,
A cargo condition estimation unit outputs a cargo condition relating to the condition of the cargo handled by the industrial vehicle, based on the work condition output by the work condition estimation unit.
The system includes a work state correction unit that corrects the work state output by the work state estimation unit based on the work state output by the work state estimation unit and the cargo state output by the cargo state estimation unit,
The work state estimation unit performs machine learning by inputting operation information relating to the operating state of the industrial vehicle and correct data on the working state of the industrial vehicle .
The aforementioned luggage status indicates either no luggage or luggage present.
The aforementioned luggage state estimation unit uses a luggage state estimation model to prohibit transitions in the luggage state other than those specified for the operation.
A control device for an industrial vehicle, wherein the work state correction unit outputs the work state output by the work state estimation unit as the corrected work state if the work state output by the work state estimation unit and the presence or absence of the cargo in the cargo state match, and corrects the work state output by the work state estimation unit to match the cargo state and outputs it as the corrected work state if the work state output by the work state estimation unit and the presence or absence of the cargo in the cargo state do not match . The control device for an industrial vehicle according to claim 1, wherein the work state estimation unit receives the current operation information as input and outputs the current work state based on the learning results. The control device for an industrial vehicle according to claim 1, wherein the operation information includes at least one of the accelerator operation amount, tire angle, lift operation amount, reach operation amount, and tilt operation amount. The control device for an industrial vehicle according to claim 1, wherein the work state estimation unit uses LSTM as a machine learning model and performs machine learning using the operation information acquired in time series as training data. A control system for an industrial vehicle having a control device for an industrial vehicle according to any one of claims 1 to 4. A program for an industrial vehicle control device used in an industrial vehicle control device according to any one of claims 1 to 4.