Fork lift, estimation system and estimation program

Abstract

To provide a fork lift which can adjust resistance values (weights) of a lever to appropriate resistance values for each operator.SOLUTION: A fork lift 1 includes a lever 14 used in operation of the fork lift 1, a resistance value estimation part, and a resistance value changing part. The lever 14 may have a lift lever, and a tilt lever. The resistance value estimation part estimates a resistance value (weight) of an appropriate lever 14 corresponding to the operator O, on the basis of a physical feature of the operator O. The resistance value changing part changes the resistance value of the lever 14, on the basis of the resistance value of the lever 14 estimated by the resistance value estimation part.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a forklift, and an estimation system and an estimation program related to the forklift. [Background technology]

[0002] There are two types of forklifts: reach forklifts and counter-loading forklifts. The number and functions of forklift levers vary depending on the type of forklift.

[0003] As disclosed in Patent Document 1, a reach forklift is equipped with a lift lever for raising and lowering the forks, a tilt lever for changing the vertical angle of the forks, a reach lever for moving the lifting device forward and backward, and an accelerator lever for traveling the forklift. Also, as disclosed in Patent Document 2, a countertop forklift is equipped with a tilt lever and an accelerator lever.

[0004] As disclosed in Patent Document 3, a lever is generally configured to swing forward or backward from a neutral position, and automatically returns to the neutral position by a spring when not in operation. However, the resistance of the lever by this spring, in other words the weight of the lever, tires the operator. Therefore, in order to reduce operator fatigue, the invention disclosed in Patent Document 3 assists the lever operation by an actuator when the amount of operation of the operating lever exceeds a predetermined value. In addition to Patent Document 3, for example, Patent Document 4 discloses a technology that assists the lever operation of a vehicle.

[0005] However, there is another problem with regard to operator fatigue caused by lever operation. Unlike ordinary passenger cars, forklifts require frequent operation of each lever, so it is preferable that the resistance value of the lever (e.g., resistance by a spring) be an appropriate value for each driver. This appropriate value depends on the gender, muscle strength, and other factors of each driver. Therefore, if a unique forklift is assigned to each driver, a method can be considered in which the resistance value of the lever of each forklift is adjusted to an appropriate resistance value corresponding to each driver. However, unlike passenger cars, a single forklift may be operated by multiple drivers in turn, so there is a problem with adopting this method. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] JP 2016-47745 A [Patent Document 2] JP 2017-88390 A [Patent Document 3] JP 2002-370898 A [Patent Document 4] JP 2003-301942 A Summary of the Invention [Problem to be solved by the invention]

[0007] Therefore, an object of the present invention is to provide a forklift truck that can adjust the resistance value of the lever, in other words, the weight of the lever, to an appropriate resistance value for each operator. [Means for solving the problem]

[0008] In order to solve the above problems, the forklift of the present invention includes a lever used to operate the forklift, a resistance value estimation unit that estimates an appropriate lever resistance value for a driver based on the driver's physical characteristics, and a resistance value change unit that changes the resistance value of the lever based on the resistance value of the lever estimated by the resistance value estimation unit.

[0009] The forklift preferably further includes a camera that photographs the driver, and a first trained model that uses images of a plurality of people and the weight of the person corresponding to each image as training data, and that has been trained to output the weight of the driver when an image of the driver generated by the camera is input, and the resistance value estimation unit estimates an appropriate lever resistance value based on the driver's weight output by the first trained model.

[0010] The forklift preferably further includes a camera that photographs the driver, and a second trained model that uses images of a plurality of people and the muscle mass corresponding to each person's image as training data and is trained to output the driver's muscle mass when an image of the driver generated by the camera is input, and the resistance value estimation unit estimates an appropriate lever resistance value based on the driver's muscle mass output by the second trained model.

[0011] The forklift preferably further includes a camera that captures the driver's face, and a third trained model that uses multiple facial images and the ages of the people corresponding to each facial image as training data and is trained to output the driver's age when a facial image of the driver generated by the camera is input, and the resistance value estimation unit estimates an appropriate lever resistance value based on the driver's age output by the third trained model.

[0012] In the forklift, the camera is preferably configured to capture an image of the driver wearing specified clothing, and the training data of the image of a person is an image of a person wearing the specified clothing.

[0013] In the forklift, the camera is preferably configured to capture an image of a driver wearing a helmet, and the training data of the face image is a face image of a person wearing the helmet.

[0014] In the forklift, the camera is preferably configured to detect a person wearing specific clothing as the driver and automatically photograph the person.

[0015] The forklift preferably further includes a characteristic memory unit that stores the physical characteristics of the driver in advance, and the resistance value estimation unit estimates an appropriate lever resistance value for the driver based on the physical characteristics of the driver stored in the characteristic memory unit.

[0016] The forklift preferably further includes a feature memory unit that pre-stores the physical features of a plurality of drivers together with corresponding facial images, a camera that photographs the faces of the drivers, and a driver identification unit that identifies the drivers stored in the feature memory unit based on the facial images generated by the camera, and the resistance value estimation unit estimates an appropriate lever resistance value for the driver based on the physical features corresponding to the identified driver.

[0017] In order to solve the above problem, the estimation system of the present invention includes a lever, a resistance value estimation unit that estimates an appropriate lever resistance value for a driver based on the driver's physical characteristics, and a resistance value change unit that changes the resistance value of the lever based on the estimated appropriate lever resistance value.

[0018] In order to solve the above problems, the estimation program of the present invention is a program used in a forklift having a lever, a resistance value changing unit that changes the resistance value of the lever based on an estimated appropriate resistance value of the lever, and a computer, and causes the computer to be executed as a resistance value estimation unit that estimates an appropriate lever resistance value for a driver based on the driver's physical characteristics. Effect of the Invention

[0019] The forklift according to the present invention allows the resistance value of the lever to be adjusted to an appropriate resistance value for each operator. [Brief description of the drawings]

[0020] [Figure 1] 1 is a front view of a forklift according to an embodiment of the present invention. [Diagram 2] FIG. 2 is a diagram showing a driver photographed by a camera. [Diagram 3] FIG. 2 is a functional block diagram of a control unit. [Figure 4] FIG. 13 is a functional block diagram showing a modified example of the control unit. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0021] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, a forklift, an estimation system, and an estimation program according to an embodiment of the present invention will be described with reference to the accompanying drawings.

[0022] Fig. 1 is a front view of a forklift 1 according to this embodiment. The forklift 1 is a battery-powered countertop forklift. As shown in Fig. 1, the forklift 1 includes a plurality of wheels 10, a vehicle body 11, a driver's seat 12, a head guard 13, a lever 14, left and right masts 15, left and right forks 16, a camera 17, a resistance value changing unit 18 (see Fig. 3), and a control unit 20 (see Fig. 3).

[0023] A plurality of wheels 10 are provided on all four sides of a vehicle body 11. A driver's seat 12 is provided on the vehicle body 11, and a head guard 13 is provided above the driver's seat 12.

[0024] The lever 14 has a lift lever and a tilt lever, and is provided in front of the driver's seat 12. The lever 14 may also have a slide lever for sliding the fork 16 left and right.

[0025] The left and right forks 16 are configured to be able to be raised and lowered via the left and right masts 15, and the driver O operates a lift lever to raise and lower the forks 16 to perform loading and unloading work.

[0026] The camera 17 is fixed to the head guard 13 and configured to capture an image of the entire body of the driver O standing on the side of the vehicle body 11. As shown in Figs. 1 and 2, the driver O is photographed at least from the front and side at the side of the forklift 1 while wearing a helmet H and a uniform U. The uniform U corresponds to the "predetermined clothing" of the present invention. The camera 17 may be a video camera. The camera 17 may be configured to detect, for example, a person wearing the uniform U (i.e., the driver O) as the driver O, and automatically capture an image of the person when the driver O approaches the forklift 1. The camera 17 may be configured to include a plurality of cameras 17.

[0027] The camera 17 also captures the face of the driver O wearing the helmet H to generate a facial image. The whole-body image and facial image generated by the camera 17 are transmitted to the control unit 20.

[0028] When capturing an image with the camera 17, the forklift 1 may issue a voice message to the driver O, such as "Please look forward" or "Please look to the side."

[0029] The resistance value changing unit 18 changes the resistance value of the lever 14 when operated by the driver O, based on the resistance value of the lever 14 estimated by a resistance value estimating unit 24 described later. The resistance value changing unit 18 is configured by, for example, a device capable of adjusting the resistance value by hydraulic pressure, or a device capable of adjusting the resistance value by a spring.

[0030] Also, for example, the resistance value changing unit 18 may be an assisting device that assists in the operation of the lever 14 against the resistance. In this case, the resistance value changing unit 18 may adjust the assisting force based on the resistance value of the lever 14 estimated by the resistance value estimating unit 24, and may substantially change the resistance value of the lever 14 when the driver O operates it.

[0031] Alternatively, the resistance value changing unit 18 may be configured to change the magnitude of the power of each device responsive to the amount of operation of the lever 14 based on the resistance value of the lever 14 estimated by the resistance value estimating unit 24. In this way, the resistance value changing unit 18 effectively changes the resistance value of the lever 14.

[0032] The control unit 20 is configured by a computer arranged in the vehicle body 11, and has an arithmetic unit, a storage device, and a memory. The storage device stores an estimation program that causes the computer to function as a resistance value estimation unit 24, which will be described later.

[0033] Fig. 3 is a functional block diagram of the forklift 1. As shown in Fig. 3, the control unit 20 has a body weight estimation unit 21, a muscle mass estimation unit 22, an age estimation unit 23, and a resistance value estimation unit 24.

[0034] The weight estimation unit 21 corresponds to the "first trained model" of the present invention. The weight estimation unit 21 is trained in advance by a neural network using deep learning to use images of multiple people and the weights of the people corresponding to each image as teacher data, and to output the weight of the driver O when an image of the driver O generated by the camera 17 is input. Thus, when an image generated by the camera 17 is input, the weight estimation unit 21 estimates the weight of the driver O and transmits the estimated weight to the resistance value estimation unit 24.

[0035] The muscle mass estimation unit 22 corresponds to the "second trained model" of the present invention. The muscle mass estimation unit 22 learns in advance, by a neural network using deep learning, to output the muscle mass of the driver O when an image of the driver O generated by the camera 17 is input, using images of a plurality of people and muscle mass corresponding to each image as teacher data. Thus, when an image generated by the camera 17 is input, the muscle mass estimation unit 22 estimates the muscle mass of the driver O and transmits the estimated muscle mass to the resistance value estimation unit 24.

[0036] The images of people in the teacher data used by the weight estimation unit 21 and the muscle mass estimation unit 22 include facial images of both men and women. This allows the weight estimation unit 21 and the muscle mass estimation unit 22 to more appropriately estimate the weight and muscle mass of the driver O, respectively, taking into account the gender.

[0037] The image of a person among the teacher data used for learning by the body weight estimation unit 21 and the muscle mass estimation unit 22 may be, for example, an image of a person wearing a uniform U. The uniform U may also be processed to make it easier to estimate the body weight and muscle mass. This allows the body weight estimation unit 21 and the muscle mass estimation unit 22 to more appropriately estimate the body weight and muscle mass of the driver O, respectively.

[0038] The age estimation unit 23 corresponds to the "third trained model" of the present invention. The age estimation unit 23 uses a neural network using deep learning to learn in advance to output the age of the driver O when a facial image of the driver O generated by the camera 17 is input, using multiple facial images and the age of the person corresponding to each facial image as teacher data. As a result, when a facial image generated by the camera 17 is input, the age estimation unit 23 estimates the age of the driver O and transmits the estimated age to the resistance value estimation unit 24.

[0039] The facial images of both men and women are included in the training data used by the age estimation unit 23. This allows the age estimation unit 23 to more appropriately estimate the age of the driver O by taking the gender into account.

[0040] The face image among the teacher data used for learning by the age estimation unit 23 may be, for example, a face image of a person wearing a helmet H. This allows the age estimation unit 23 to estimate the age of the driver O more appropriately.

[0041] The resistance value estimation unit 24 estimates an appropriate resistance value of the lever 14 based on the weight, muscle mass, and age of the driver O estimated by the weight estimation unit 21, muscle mass estimation unit 22, and age estimation unit .

[0042] For example, the resistance value estimation unit 24 may estimate a stronger resistance value of the lever 14 the heavier the weight estimated by the weight estimation unit 21. Also, the resistance value estimation unit 24 may estimate a stronger resistance value of the lever 14 the greater the muscle mass estimated by the muscle mass estimation unit 22. Furthermore, the resistance value estimation unit 24 may estimate a stronger resistance value of the lever 14 the younger the age estimated by the age estimation unit 23.

[0043] In addition, the resistance value estimation unit 24 may weaken the estimated resistance value of the lever 14 if the estimated weight is heavy but the estimated muscle mass is less than a certain amount, or may weaken the estimated resistance value of the lever 14 depending on the estimated age even if the estimated muscle mass is high.

[0044] In this way, there is no limitation on the weighting of body weight, muscle mass, and age for the resistance value of the lever 14 estimated by the resistance value estimation unit 24. Also, the resistance value of the lever 14 appropriate for each driver O estimated by the resistance value estimation unit 24 does not have to estimate the resistance values ​​of all levers of the lever 14. In other words, the resistance value estimation unit 24 only needs to estimate the resistance value of the lift lever or the tilt lever.

[0045] The resistance value changing unit 18 changes the resistance value of each lever based on the appropriate resistance value estimated by the resistance value estimating unit 24.

[0046] The forklift 1 according to this embodiment is configured as described above, and therefore can provide the driver O with an appropriate resistance value of the lever 14.

[0047] Although an embodiment of the forklift, the estimation system, and the estimation program according to the present invention has been described above, the present invention is not limited to the above embodiment. The forklift, the estimation system, and the estimation program according to the present invention may be implemented, for example, in each of the following modified examples or in a combination of the modified examples.

[0048] <Modification> The forklift 1 may be a reach forklift. In this case, the lever 14 may include an accelerator lever. The forklift 1 may be an engine-powered forklift.

[0049] For example, if the weight estimation unit 21 and the muscle mass estimation unit 22 can estimate the weight and muscle mass of the driver O from an image of a part of the driver O's body, the camera 17 may be configured to capture only a part of the driver O's body.

[0050] In the above embodiment, the resistance value estimation unit 24 estimated an appropriate resistance value of the lever 14 for the driver O by referring to the driver's body weight, muscle mass, and age. However, the resistance value estimation unit 24 may estimate an appropriate resistance value of the lever 14 by referring to, for example, any one of the driver's body weight, muscle mass, and age.

[0051] The control unit 20 may have a characteristic storage unit 25 that stores the physical characteristics (weight, muscle mass, age) of each driver O in advance, instead of the weight estimation unit 21, the muscle mass estimation unit 22, and the age estimation unit .

[0052] In this case, the forklift 1 may further include an input unit that accepts input of a name, identifier, etc. corresponding to each driver O, or input of a tool that identifies each driver O, such as an ID card, and the resistance value estimation unit 24 may identify the driver O based on the input name, identifier, etc., or input of the above-mentioned tool, and estimate an appropriate resistance value of the lever 14 by referring to the physical characteristics of the driver O.

[0053] Furthermore, when the control unit 20 has the characteristic memory unit 25, the forklift 1 is provided with a face camera (camera 17) for photographing the face of the driver O, for example, in the driver's seat 12, and as shown in FIG. 4, the control unit 20 further has a driver identification unit 26 for identifying the driver O stored in the characteristic memory unit 25 based on the face image generated by the face camera, and the resistance value estimation unit 24 may estimate an appropriate resistance value of the lever 14 based on the physical characteristics of the identified driver O.

[0054] Furthermore, in addition to the case where the control unit 20 has the characteristic memory unit 25, if the helmet H has a tag, a QR code (registered trademark), etc. that identifies each driver O, each driver O may be identified by a tool that detects them, and the resistance value estimation unit 24 may estimate an appropriate resistance value of the lever 14 based on the physical characteristics of the identified driver O.

[0055] The control unit 20 may be configured, for example, by a server computer provided on a cloud, and the forklift 1 may estimate an appropriate resistance value of the lever 14 corresponding to the driver O by communicating with this server computer. [Explanation of symbols]

[0056] O Driver H Helmet U uniform 1. Forklift 10 wheels 11 Body 12 Driver's seat 13 Head Guard 14 Lever 15 Mast 16 Fork 17 Camera 18 Resistance value change section 20 Control section 21 Weight Estimation Section 22 Muscle mass estimation section 23 Age Estimation Department 24 Resistance value estimation section 25 Feature Memory Unit 26 Driver Identification Department

Claims

1. A lever used to operate a forklift; A resistance value estimation unit that estimates an appropriate resistance value of the lever for a driver based on a physical characteristic of the driver; a resistance value changing unit that changes the resistance value of the lever based on the resistance value of the lever estimated by the resistance value estimating unit.

2. A camera for photographing the driver; a first trained model that uses images of a plurality of people and weights of the people corresponding to the images of the people as training data, and that has been trained to output the weight of the driver when an image of the driver generated by the camera is input; The forklift according to claim 1 , wherein the resistance value estimation unit estimates an appropriate resistance value of the lever based on the weight of the driver output by the first trained model.

3. A camera for photographing the driver; A second trained model is further provided, which is trained to output the muscle mass of a driver when an image of the driver generated by the camera is input, using images of a plurality of people and muscle mass corresponding to each of the images of the people as training data, The forklift according to claim 1 , wherein the resistance value estimation unit estimates an appropriate resistance value of the lever based on a muscle mass of the driver output by the second trained model.

4. A camera for photographing the face of the driver; A third trained model is further provided, which is trained to output the age of the driver when a face image of the driver generated by the camera is input, using a plurality of face images and the age of the person corresponding to each of the face images as training data, The forklift according to claim 1 , wherein the resistance value estimation unit estimates an appropriate resistance value of the lever based on the age of the driver output by the third trained model.

5. The camera is configured to capture an image of the driver wearing a predetermined outfit; 4. The forklift according to claim 2, wherein the training data of the image of a person is an image of a person wearing the predetermined clothing.

6. The camera is configured to capture an image of the driver wearing a helmet; 5. The forklift according to claim 4, wherein the training data of the facial image is a facial image of a person wearing the helmet.

7. The forklift according to claim 5 , wherein the camera is configured to detect a person wearing the specified clothing as the driver and automatically photograph the person.

8. A characteristic storage unit that stores the physical characteristics of the driver in advance, The forklift according to claim 1 , wherein the resistance value estimation unit estimates an appropriate resistance value of the lever for the driver based on physical characteristics of the driver stored in the characteristic storage unit.

9. a feature storage unit that stores in advance the physical features of a plurality of the drivers together with corresponding facial images; A camera for photographing the face of the driver; A driver identification unit that identifies the driver stored in the characteristic storage unit based on a face image generated by the camera, The forklift according to claim 8 , wherein the resistance value estimation unit estimates an appropriate resistance value of the lever for the identified driver based on the physical characteristics corresponding to the identified driver.

10. Lever and A resistance value estimation unit that estimates an appropriate resistance value of the lever for a driver based on a physical characteristic of the driver; and a resistance value changing unit that changes the resistance value of the lever based on the estimated appropriate resistance value of the lever.

11. Lever and a resistance value changing unit that changes a resistance value of the lever based on the estimated appropriate resistance value of the lever; A program for use in a forklift having a computer, The computer, and an estimation program executed by the resistance value estimation unit to estimate an appropriate resistance value of the lever for the driver based on the physical characteristics of the driver.

Images