Safety device and picking forklift comprising same

Abstract

The invention provides a safety device and a picking forklift comprising the same, which can further accurately determine the state of an operator and a belt, such as whether the operator wears the belt. The present invention comprises: a band to be worn by an operator; an imaging unit that captures an image of the console; and a wearing determination unit that determines whether or not the operator wears the belt, the wearing determination unit including: a collection unit that collects an image of the state of the operator and the belt; a learning model generation unit that generates and stores a learning model by machine learning; an acquisition unit that acquires an image of the state of the operator and the belt at the current time by means of the imaging unit; a prediction unit that predicts the state of the operator and the belt by inputting the image at the current time acquired from the acquisition unit into the learning model generated by the learning model generation unit; and a determination unit that determines whether to issue a warning to the operator on the basis of the prediction unit.

Description

Technical Field

[0001] The present invention relates to a safety device for preventing an operator riding on a driver's cab of a picking forklift from falling off the driver's cab and a picking forklift including the same. Background Art

[0002] A picking forklift includes a driver's cab that can be lifted and lowered along a mast, and a pair of left and right forks protruding rearward from the driver's cab. In the loading and unloading operation using the picking forklift, a pallet is inserted into the forks, and the driver's cab carrying the operator moves to a high place, and the operator can unload goods between the shelf and the pallet.

[0003] For example, as in Patent Document 1, a picking forklift includes a safety device having a belt to be worn by an operator and a connecting portion that connects the belt to the picking forklift, so that the operator does not fall from the driver's cab to the ground.

[0004] Incidentally, an operator sometimes performs a loading and unloading operation on a high driver's cab without wearing the belt on the body because the operator thinks that wearing the belt is troublesome or hates being restricted. This operation is very dangerous. Therefore, in Patent Document 1, the safety device includes a wearing determination unit that determines whether the operator is wearing the belt, and based on the determination result of the wearing determination unit, warns the operator to wear the belt, thereby preventing the operator from falling accidents.

[0005] The wearing determination unit of the safety device determines whether the operator is wearing the belt by detecting a mark attached to the belt using an image reading device. However, depending on the position of the belt worn by the operator, there are problems that the image reading device has difficulty detecting the mark or misdetects it.

[0006] [Prior Art Documents]

[0007] [Patent Documents]

[0008] [Patent Document 1] Japanese Patent Laid-Open No. 2015-224114 Summary of the Invention

[0009] [Problems to be Solved by the Invention]

[0010] Therefore, the subject to be solved by the present invention is to provide a safety device that can more accurately determine whether an operator is wearing a belt or the like and the state of the operator and the belt, and a picking forklift including the same.

[0011] [Technical Means for Solving the Problems]

[0012] In order to solve the above subject, the safety device of the present invention is for preventing an operator riding on a driver's cab of a picking forklift from falling,

[0013] The safety device includes:

[0014] A belt for the operator to wear;

[0015] A camera unit for photographing the bridge; and

[0016] A wearing determination unit for determining whether the operator is wearing the belt,

[0017] The wearing determination unit includes:

[0018] A collection unit for collecting images of the state of the operator and the belt;

[0019] A learning model generation unit for generating and storing a learning model through machine learning;

[0020] An acquisition unit for acquiring an image of the state of the operator and the belt at the current time using the camera unit;

[0021] A prediction unit for predicting the state of the operator and the belt by inputting the image at the current time obtained from the acquisition unit into the learning model generated by the learning model generation unit; and

[0022] A decision unit for deciding whether to issue a warning to the operator based on the prediction unit.

[0023] Preferably, the state of the operator and the belt includes the state during the process of the operator wearing the belt.

[0024] In addition, the picking forklift of the present invention includes:

[0025] The said safety device;

[0026] A warning unit for warning the operator to wear the belt; and

[0027] A vehicle control unit for controlling the warning unit.

[0028] Preferably, the vehicle control unit controls in the following manner: when it is determined by the wearing determination unit that the belt is not worn by the operator, the warning unit is operated, and thereafter, when it is determined that the operator is in the state of wearing the belt halfway, the warning unit is operated until a specified set time has elapsed, and when the set time has elapsed, the warning unit is stopped and the operation of the picking forklift cannot be performed.

[0029] [Effects of the Invention]

[0030] In the safety device of the present invention and the picking forklift including the same, it is possible to more accurately determine whether the operator is wearing the belt. Description of the Drawings

[0031] Figure 1 It is a side view showing a picking forklift including the safety device of the present invention.

[0032] Figure 2 It is a block diagram showing the structure of the picking forklift.

[0033] Figures 3A - 3C It is a side view showing the first to third states of the operator and the belt.

[0034] Figure 4A , Figure 4B It is a side view showing the fourth and fifth states of the operator and the belt.

[0035] Figure 5 It is a block diagram showing the wearing determination unit.

[0036] Figure 6 It is a flowchart showing the control method of the safety device.

[0037] [Description of Symbols]

[0038] 1: Order picking forklift

[0039] 4: Cab

[0040] 10: Safety device

[0041] 11: Belt

[0042] 14: Imaging unit

[0043] 15: Wearing determination unit

[0044] 20: Vehicle control unit

[0045] 25: Warning unit

[0046] 40: Collection unit

[0047] 41: Learning model generation unit

[0048] 42: Prediction unit

[0049] 45: Acquisition unit

[0050] 43: Decision unit

[0051] O: Operator Detailed implementation manner

[0052] Hereinafter, an embodiment of the safety device of the present invention and the order picking forklift including the same will be described based on the drawings.

[0053] As Figure 1 and Figure 2 shown, the order picking forklift 1 includes: a vehicle body portion 2 that houses a traveling portion 21, a hydraulic portion 22, etc.; a mast 3 that is erected behind the vehicle body portion 2; a cab 4 that moves up and down along the mast 3; and a pair of left and right forks 8 that protrude rearward from the cab 4. The traveling portion 21 includes a traveling motor for rotating the wheels, a swivel motor for swiveling the wheels, etc. The hydraulic portion 22 includes a hydraulic tank and a hydraulic pump for raising and lowering the cab 4.

[0054] The driver's cab 4 has a chassis 5, a front frame 6 and a top cover 7, and an operation panel 9 provided on the front frame 6. In addition to a key switch for starting the order picking forklift 1, the operation panel 9 is also provided with a steering wheel or an operating lever for indicating the travel of the order picking forklift 1 or the lifting of the driver's cab 4.

[0055] The order picking forklift 1 includes a safety device 10, and the safety device 10 includes a belt 11, a connecting part 12 and a winding part 13. The belt 11 is worn around the waist of an operator O riding on the driver's cab 4. One end of the connecting part 12 is mounted on the belt 11, and the other end is mounted on the winding part 13.

[0056] In addition, the winding part 13 is fixed to the top cover 7 of the driver's cab 4. A part from one end of the connecting part 12 to 1 m is always pulled out from the winding part 13. If a tension is applied, the remaining part is pulled out due to the tension. Moreover, if a large tension is applied to the connecting part 12, the winding part 13 restrains the pulling out of the connecting part 12. Thus, even if the operator O falls from the high driver's cab 4, the operator O will be suspended near the driver's cab 4 and will not collide with the ground.

[0057] In the loading and unloading operation using the order picking forklift 1, a pallet P is inserted into the fork 8, and the driver's cab 4 on which the operator O rides moves to a high place, and the operator O can perform the loading and unloading operation of unloading the high - placed goods B between the shelf and the pallet P.

[0058] The safety device 10 includes an imaging part 14 including a Charge Coupled Device (CCD) camera, etc. The imaging part 14 is provided below the operation panel 9 and faces in such a way as to reflect the lower body of the operator O riding on the driver's cab 4, and can determine the state of the operator O and the belt 11. The imaging part 14 acquires image data at a specified interval, such as 30 frames per second.

[0059] The safety device 10 includes a belt detection part 16. The belt detection part 16 includes a latching part such as a hook provided on the upper part of the front frame 6 of the driver's cab 4 to hold the belt 11. In addition, the belt detection part 16 includes a weight sensor or a vibration sensor, etc. in the latching part such as a hook to detect the belt 11 held by the latching part. By the operator O removing the belt 11 from the body and hooking the belt 11 on the belt detection part 16, the belt detection part 16 detects the belt 11 and can detect that the belt 11 is not worn on the operator O.

[0060] In addition, the safety device 10 includes a wearing determination unit 15. The wearing determination unit 15 includes a microprocessor (MicroProcessor Unit, MPU), and is configured to determine whether the belt 11 is worn by the operator O or the like, and the state of the operator O and the belt 11 based on the image captured by the imaging unit 14, and decide whether to issue a warning to the operator O or the like to control the order picking forklift 1.

[0061] The order picking forklift 1 includes a warning unit 25. The warning unit 25 is configured to issue a warning to the operator to wear the belt 11 when the belt 11 is not worn by the operator O. The warning unit 25 includes a lamp or a buzzer provided on the front frame 6 of the driver's cab 4, etc., and issues a warning to the operator O to wear the belt 11 by lighting or sounding, etc.

[0062] The order picking forklift 1 includes a vehicle control unit 20. The vehicle control unit 20 includes a microprocessor (MPU), and may be integrally formed with the wearing determination unit 15. The vehicle control unit 20 is configured to control the traveling unit 21, the hydraulic pressure unit 22, and the warning unit 25 based on the instruction to the operator O from the operation panel 9, the detection result of the belt detection unit 16, and the determination result of the wearing determination unit 15.

[0063] As Figures 3A - 3C and Figure 4A , Figure 4B shown, there are the following five states in the state of the operator O and the belt 11.

[0064] (1) As Figure 3A shown, the state where the operator O is not on the driver's cab 4 and the belt 11 is held by the belt detection unit 16 is set as the "first state".

[0065] (2) As Figure 3B shown, the state where the operator O is not on the driver's cab 4 and the belt 11 is not held by the belt detection unit 16 is set as the "second state".

[0066] (3) As Figure 3C shown, the state where the operator O is on the driver's cab 4 and the belt 11 is not worn by the operator O is set as the "third state".

[0067] (4) As Figure 4A shown, the state where the operator O is on the driver's cab 4 and the belt 11 is worn by the operator O is set as the "fourth state".

[0068] (5) As Figure 4B shown, the state where the operator O is on the driver's cab 4 and the belt 11 is being worn by the operator O is set as the "fifth state".

[0069] As Figure 5As shown, the wearing determination unit 15 includes a collection unit 40 that collects, as input data 46 of the teacher data, the feature amounts of images of the states (first state to fifth state) of the operator O and the belt 11. The feature amount is a value obtained by numerically representing the features of an object in an image and extracted from the image using a general method.

[0070] The wearing determination unit 15 includes a learning model generation unit 41 that performs machine learning based on the teacher data 46 collected by the collection unit 40, and generates and stores a learning model through machine learning. In the present embodiment, the learning model generation unit 41 performs supervised learning using the teacher data 46 that associates the states (first state to fifth state) of the operator O and the belt 11 with the feature amounts of the images. The learning model uses the teacher data 46 generated by the learning model generation unit 41 and outputs, as output data, the states (first state to fifth state) of the operator O and the belt 11 based on the feature amounts of the images.

[0071] The learning model generation unit 41 uses a machine learning algorithm such as a general neural network. The learning model generation unit 41 generates a learning model that estimates an output from an input, that is, a learning model that outputs output data when input data is input.

[0072] The wearing determination unit 15 includes an acquisition unit 45 that acquires, at regular intervals, input data ID that is the feature amount based on an image of the current moment captured by the imaging unit 14.

[0073] The wearing determination unit 15 includes a prediction unit 42 that predicts, as output data OD, the states (first state to fifth state) of the operator O and the belt 11 by applying the learning model generated by the learning model generation unit 41 to the input data ID of the current moment acquired by the acquisition unit 45.

[0074] The wearing determination unit 15 includes a determination unit 43. The determination unit 43 identifies the states (first state to fifth state) of the operator O and the belt 11 at the current moment based on the output data OD predicted by the prediction unit 42, and determines whether to issue a warning to the operator O to wear the belt 11 or the like. The vehicle control unit 20 is configured to control the warning unit 25 or the like based on the determination of the determination unit 43.

[0075] As Figure 6 shown, the order picker forklift 1 including the safety device 10 performs the following control.

[0076] The operator O turns on the key switch to start the order picker forklift 1 (step S1). Then, the imaging unit 14 captures an image of the driver's cab 4, and the wearing determination unit 15 acquires the captured image from the imaging unit 14 at regular intervals.

[0077] The wearing determination unit 15 determines whether the belt 11 is reflected in the image from the imaging unit 14 (step S2). When the belt 11 is reflected in the image, the wearing determination unit 15 determines whether the belt 11 is worn by the operator O (step S3). Then, when the belt 11 is in the fourth state ( Figure 4A ) worn by the operator O, the vehicle control unit 20 controls in such a manner that the traveling unit 21 and the hydraulic pressure unit 22 can be operated (step S4).

[0078] When the wearing determination unit 15 determines that the belt 11 is not reflected in the image (step S2), or when the belt 11 is reflected in the image but the belt 11 is not worn by the operator O (step S3), the wearing determination unit 15 determines whether the belt 11 is held by the belt detection unit 16 (step S5).

[0079] It is determined whether the belt detection unit 16 holds the belt 11 (step S5). When the belt 11 is in the first state ( Figure 3A ) held by the belt detection unit 16, it controls in such a manner that the traveling unit 21 and the hydraulic pressure unit 22 cannot be operated (step S11).

[0080] In addition, it is determined whether the belt detection unit 16 holds the belt 11 (step S5). When it is determined that the belt 11 is not in the second state ( Figure 3B ), the third state ( Figure 3C ) or the fifth state ( Figure 4B ) held by the belt detection unit 16, the vehicle control unit 20 controls in such a manner that the warning unit 25 operates (step S6).

[0081] Then, after the warning unit 25 operates, the wearing determination unit 15 is used to determine whether it is in the fifth state ( Figure 4B ) in the middle of the belt 11 being worn by the operator O (step S7). When it is determined by the wearing determination unit 15 that it is in the fifth state ( Figure 4B ) in the middle of the belt 11 being worn by the operator O, the vehicle control unit 20 controls in such a manner that the warning unit 25 stops (step S8).

[0082] In addition, when it is determined by the wearing determination unit 15 that it is not in the third state ( Figure 3C ) in the middle of the belt 11 being worn by the operator O (step S7), the vehicle control unit 20 starts timing this state (step S9), and returns to step S6 to continue the operation of the warning unit 25. Then, when the elapsed time is less than the specified set time, the operations of step S6, step S7, and step S9 are repeated.

[0083] Then, when the elapsed time measured has passed a prescribed set time (step S9), the vehicle control unit 20 controls as follows: stops the operation of the warning unit 25 (step S10), makes the operations of the traveling unit 21 and the hydraulic pressure unit 22 impossible (step S11), and turns off the key switch (step S12). Thereby, the operator O cannot operate the order picker forklift 1.

[0084] As described above, the preferred embodiments of the present invention have been described, but the structure of the present invention is not limited to these embodiments. For example, it can be changed as follows.

[0085] The wearing determination unit 15 does not determine only based on whether it conforms to the first state to the fifth state, and it is sufficient that it can determine the state where the belt 11 is not worn on the operator O and the state where the belt 11 is worn on the operator O.

[0086] In addition, instead of determining whether the belt detection unit 16 holds the belt 11, the wearing determination unit 15 may determine whether the belt 11 is held by a locking portion such as a hook based on the image from the imaging unit 14.

[0087] Moreover, the wearing determination unit 15 may be configured to map into the first state to the fifth state by using unsupervised learning and semi-supervised learning in addition to supervised learning as in the above-described embodiment.

[0088] Furthermore, the warning unit 25 may be configured to display a warning mark or the like on the display unit of the operation panel 9 in addition to the lamp or buzzer as in the above-described embodiment.

[0089] The effects of the present invention will be described.

[0090] The safety device 10 of the present invention is for preventing the operator O on the driver's seat 4 of the order picker forklift 1 from falling. The safety device 10 includes: a belt 11 for the operator O to wear; an imaging unit 14 for photographing the driver's seat 4; and a wearing determination unit 15 for determining whether the operator O wears the belt 11. The wearing determination unit 15 includes: a collection unit 40 for collecting images of the state of the operator O and the belt 11; a learning model generation unit 41 for generating and storing a learning model through machine learning; an acquisition unit 45 for acquiring an image of the state of the operator O and the belt 11 at the current time by using the imaging unit 14; a prediction unit 42 for predicting the state of the operator O and the belt 11 by inputting the image at the current time acquired from the acquisition unit 45 into the learning model generated by the learning model generation unit 41; and a determination unit 43 for determining whether to issue a warning to the operator O based on the prediction unit 42.

[0091] Thus, the wearing determination unit 15 of the safety device 10 predicts the state of the operator O and the belt 11 based on the image obtained by the imaging unit 14 and the learning model. Therefore, it is possible to more accurately determine whether the operator O is wearing the belt 11 and the state of the operator O and the belt 11 regardless of the position of the belt 11 worn by the operator O.

[0092] Preferably, the state of the operator O and the belt 11 includes the state during the process of the operator O wearing the belt 11.

[0093] Thus, when the wearing determination unit 15 determines that it is the state during the process of the operator O wearing the belt 11, it is the state where the belt 11 is not worn on the operator O but the operator O is about to wear the belt 11. Therefore, the operation of the order picking forklift 1 can be more appropriately performed based on this state.

[0094] In addition, the order picking forklift 1 of the present invention includes: the safety device 10; a warning unit 25 that warns the operator O to wear the belt 11; and a vehicle control unit 20 that controls the warning unit 25.

[0095] Thus, the wearing determination unit 15 of the safety device 10 determines the state of the operator O and the belt 11. Therefore, it is possible to more accurately determine the state of the operator O and the belt 11 regardless of the position of the belt 11 worn by the operator O. Therefore, according to the determination result, the warning unit 25 can appropriately warn the operator O to wear the belt 11.

[0096] Preferably, the vehicle control unit 20 controls in the following manner: when it is determined by the wearing determination unit 15 that the belt 11 is not worn on the operator O, the warning unit 25 is operated. After that, when it is determined that it is the state during the process of the operator O wearing the belt 11, the warning unit 25 is operated until a predetermined set time elapses. When the set time elapses, the warning unit 25 is stopped and the operation of the order picking forklift 1 cannot be performed.

[0097] Thus, when it is determined by the wearing determination unit 15 that the belt 11 is not worn on the operator O, the operator O can be appropriately warned to wear the belt 11. And when it is determined that it is the state during the process of the operator O wearing the belt 11, the operator O is about to wear the belt 11. Therefore, the warning by the warning unit 25 is stopped, and thus the operation of the operator O wearing the belt 11 can be not hindered. Then, the vehicle control unit 20 times the state during the process of the operator O wearing the belt 11. If the set time elapses, it is determined that the operator O cannot wear the belt 11. Therefore, the operation of the order picking forklift 1 cannot be performed, thereby preventing the operator O from falling.

Claims

1. A safety device for preventing an operator riding on a driver's cab of a picking forklift from falling, wherein the safety device comprises: a belt for the operator to wear; a camera unit for photographing the driver's cab; and a wearing determination unit for determining whether the operator wears the belt, wherein the wearing determination unit comprises: a collection unit for collecting images of the state of the operator and the belt; a learning model generation unit for generating and storing a learning model through machine learning; an acquisition unit for acquiring, by using the camera unit, images of the state of the operator and the belt at the current moment; a prediction unit for predicting the state of the operator and the belt by inputting the images at the current moment acquired from the acquisition unit into the learning model generated by the learning model generation unit; and a decision unit for deciding whether to issue a warning to the operator based on the prediction unit.

2. The safety device according to claim 1, wherein the state of the operator and the belt includes a state during the process of the operator wearing the belt.

3. A picking forklift, characterized in that comprises: the safety device according to claim 1 or 2; a warning unit for issuing a warning to the operator to wear the belt; and a vehicle control unit for controlling the warning unit.

4. The picking forklift according to claim 3, wherein the vehicle control unit controls in such a manner that when it is determined by the wearing determination unit that the belt is not worn by the operator, the warning unit is operated, and thereafter, when it is determined that the operator is in a state during the process of wearing the belt, the warning unit is operated until a prescribed set time has elapsed, and when the set time has elapsed, the warning unit is stopped and the operation of the picking forklift is disabled.

Images