JP2022147047A - Forklift and cargo handling system - Google Patents

Abstract

To provide a forklift that is able to prompt an operator more appropriately to pay attention.SOLUTION: A forklift 200A that performs a cargo handling operation in a working area, includes: an image data generation unit 203 that photographs an image in a traveling direction of a vehicle body and generates image data; a learning model unit 204 having machine-learned so as to generate a safety score indicating a degree of safety of a traveling route of the vehicle body; a processing unit 205 that acquires a safety score from the learning model unit 204 by inputting the image data to the learning model unit 204; an illuminating unit 201 that emits notification light to a road surface in the traveling direction; and a control unit 208 that controls the illuminating unit 201, wherein the control unit 208 changes an output mode for the notification light, based on the safety score.SELECTED DRAWING: Figure 1

Description

The present invention relates to forklifts and cargo handling systems.

2. Description of the Related Art Conventionally, forklifts are known that travel while illuminating a road surface with notification light for the purpose of alerting workers (including other forklift operators) in the workplace (see, for example, Patent Document 1). However, since the conventional forklift has a constant output mode of the notification light, it is insufficient to alert the operator.

Japanese Patent Application No. 2000-344005

SUMMARY OF THE INVENTION The present invention has been made in view of the above circumstances, and an object thereof is to provide a forklift truck and a cargo handling system capable of prompting a worker to be alerted more appropriately.

In order to solve the above problems, the forklift according to the present invention includes:
A forklift that performs cargo handling work in a workshop,
a vehicle body;
an image data generating unit that captures an image of the traveling direction of the vehicle body and generates image data;
a learning model unit that is machine-learned to generate a safety score indicating the degree of safety of a travel route of the vehicle body using a machine learning algorithm having predetermined parameters when the image data is input;
a processing unit that acquires the safety score from the learning model unit by inputting the image data into the learning model unit;
a lighting unit that emits notification light toward the road surface in the traveling direction;
A control unit that controls the lighting unit,
The control unit
The output mode of the notification light is changed based on the safety score.

In this configuration, since the output mode of the notification light is changed based on the safety score indicating the degree of safety of the travel route of the vehicle body, it is possible to prompt the worker to be alerted more appropriately.

The forklift above
a position estimation unit that estimates the self-position;
a map generator that generates an environment map showing the distribution of the safety scores in the workplace;
The map generation unit
The safety score acquired from the processing unit is defined as a current score, the safety score at the self-position within the environment map is defined as a past score, and the current score and the past score are compared to determine which one has the lowest safety score. outputting the safety score of to the control unit;
The control unit
The output mode of the notification light can be changed based on the safety score acquired from the map generator.

The forklift above
a position estimation unit that estimates the self-position;
an information acquisition unit that acquires the position of another vehicle related to the position of the work vehicle traveling in the workshop;
with
The processing unit is
changing the degree of safety of the safety score acquired from the learning model unit according to the distance between the self position and the other vehicle position, and outputting the safety score to the control unit;
The control unit
The output mode of the notification light can be changed based on the safety score acquired from the processing unit.

In order to solve the above problems, the cargo handling system according to the present invention includes:
A cargo handling system comprising a management device and at least one forklift that performs cargo handling work in a workplace under the management of the management device,
The forklift is
a vehicle body;
an image data generating unit that captures an image of the traveling direction of the vehicle body and generates image data;
a learning model unit that is machine-learned to generate a safety score indicating the degree of safety of a travel route of the vehicle body using a machine learning algorithm having predetermined parameters when the image data is input;
a processing unit that acquires the safety score from the learning model unit by inputting the image data into the learning model unit;
a lighting unit that emits notification light toward the road surface in the traveling direction;
A control unit that controls the lighting unit,
The control unit
The output mode of the notification light is changed based on the safety score.

In the above cargo handling system,
The forklift includes a position estimation unit that estimates its own position,
The management device
a communication unit for obtaining the safety score and the self-location from the forklift;
a map generator that generates an environment map showing the distribution of the safety scores in the workplace;
The map generation unit
The safety score obtained from the forklift is used as a current score, the safety score at the self-position of the forklift in the environment map is used as a past score, and the current score and the past score are compared to determine safety. transmitting the lower safety score to the controller of the forklift;
The control unit
The output mode of the notification light can be changed based on the safety score acquired from the map generator.

In the above cargo handling system,
The forklift includes a position estimation unit that estimates its own position,
The management device
an information acquisition unit that acquires the self-position of the forklift and the position of other vehicles related to the position of the work vehicle traveling in the workshop;
a calculation unit that calculates the distance between the self position and the position of the other vehicle;
with
The processing unit is
according to the distance obtained from the calculation unit, changing the degree of safety of the safety score obtained from the learning model unit and outputting it to the control unit;
The control unit
The output mode of the notification light can be changed based on the safety score acquired from the processing unit.

In the above cargo handling system,
The processing unit transmits image data with a safety score, in which the safety score obtained from the learning model unit is associated with the image data input to the learning model unit, to the management device,
The management device
a collection unit that collects the image data with the safety score and generates learning data;
a parameter updating unit that performs machine learning based on the learning data, generates update data for updating the parameters included in the learning model unit, and transmits the update data to the learning model unit;
with
The learning model unit can be configured to update the parameters based on the update data.

According to the present invention, it is possible to provide a forklift truck and a cargo handling system capable of prompting a worker to be alerted more appropriately.

1 is a block diagram of a cargo handling system according to a first embodiment; FIG. 1 is a side view of a forklift according to a first embodiment; FIG. 1 is a plan view of a cargo handling system according to a first embodiment; FIG. 4A is a model diagram displayed on the management device according to the first embodiment; FIG. (B) is a model diagram (environmental map) generated by the map generator of the forklift according to the first embodiment; It is a block diagram of the cargo handling system concerning a 2nd embodiment. FIG. 11 is a block diagram of a cargo handling system according to a third embodiment; FIG. FIG. 11 is a plan view showing the positional relationship between a forklift and another working vehicle in the cargo handling system according to the third embodiment; It is a block diagram of a cargo handling system concerning a 4th embodiment. It is a block diagram of a cargo handling system concerning a 5th embodiment. It is a side view of the forklift concerning 5th Embodiment.

BEST MODE FOR CARRYING OUT THE INVENTION Hereinafter, embodiments of a forklift and a cargo handling system according to the present invention will be described with reference to the accompanying drawings.

[First embodiment]
FIG. 1 shows a block diagram of a cargo handling system 1A according to the first embodiment of the present invention. The cargo handling system 1A includes a management device 100A and at least one laser-guided unmanned forklift 200A (corresponding to the "forklift" of the present invention).

100 A of management apparatuses are provided with the communication part 101, the integrated control part 102, and the display part 103. FIG. As shown in FIG. 3, the management device 100A may be provided outside the workplace 2 (in this embodiment, a warehouse having a plurality of racks 3) where the unmanned forklift 200A travels, or may be provided inside the workplace 2. good too.

The communication unit 101 is configured to wirelessly communicate with the unmanned forklift 200A registered in advance in the management device 100A.

The integrated control unit 102 is configured to manage travel and cargo handling work of the unmanned forklift 200A. For example, the integrated control unit 102 creates a cargo handling schedule for the unmanned forklift 200A and determines a travel route for smooth cargo handling. The integrated control unit 102 notifies the unmanned forklift truck 200A of the travel route via the communication unit 101 .

The display unit 103 is composed of, for example, a liquid crystal display. The display unit 103 displays travel information and cargo handling work information of the unmanned forklift 200A. As shown in FIG. 4A, the display unit 103 may display a model diagram M1 of the workplace 2, and display the current location Ma, travel route Ra, and the like of the unmanned forklift 200A in the model diagram M1 as travel information.

The unmanned forklift 200A is configured to travel and perform cargo handling work under the control of the management device 100A. As shown in FIG. 2 , the unmanned forklift 200A includes a vehicle body 210 , a cargo handling device 211 , and a laser scanner 212 provided on the upper portion of the vehicle body 210 . The cargo handling device 211 includes a mast horizontally movable in front and rear of the vehicle body 210 and a fork vertically movable on the mast.

As shown in FIG. 3 , the laser scanner 212 projects a laser L around while rotating the laser light source, and detects the reflected light L′ from the plurality of reflectors 4 arranged in the workplace 2 . A calculation unit of the laser scanner 212 stores the position of the reflector 4 on a predetermined map, and calculates the current position (self-position) of the vehicle body 210 based on the principle of triangulation. In this manner, unmanned forklift 200A travels along the notified travel route while acquiring current location information regarding the current location of vehicle body 210 .

Referring to FIG. 1 again, unmanned forklift 200A includes illumination unit 201, alarm sound output unit 202, image data generation unit 203, learning model unit 204, processing unit 205, position estimation unit 206, map A generation unit 207 and a control unit 208 are provided.

The lighting unit 201 is composed of, for example, at least one LED light, and emits notification light toward the road surface in the traveling direction of the vehicle body 210 under the control of the control unit 208 . As shown in FIG. 2, the unmanned forklift 200A mainly travels with the forks facing in the opposite direction to the direction of travel, so the illumination unit 201 emits notification light toward the road surface on the opposite side of the forks. The illumination unit 201 includes an LED light that emits notification light toward the road surface on the side of the forks so that the notification light can be emitted toward the road surface in the direction of travel even when the forks face the direction of travel during running. It may contain further.

In this embodiment, the image of the notification light that appears on the road surface is circular with an ambiguous outline. may have been Moreover, the color of the notification light is preferably a color that stands out against the road surface in order to enhance the notification effect. For example, when the color of the road surface is white or light gray, colors with high saturation such as blue, red, and green are preferable.

Furthermore, the lighting unit 201 is configured to change the output mode of the notification light under the control of the control unit 208 . The output modes in the present embodiment vary the flashing speed of the notification light, and specifically include five patterns of constant lighting, slow flashing, medium speed flashing, high speed flashing, and off.

The alarm sound output unit 202 is composed of at least one speaker, for example, and outputs an alarm sound under the control of the control unit 208 . Further, when an obstacle sensor is provided on the vehicle body 210, when the obstacle sensor detects an obstacle existing around the vehicle body 210 (for example, luggage placed on the travel route), an alarm sound output unit 202 may output an audible alarm.

The image data generator 203 is configured to include at least one photographing means and image processing means. The image capturing means captures an image (still image and/or moving image) including the traveling direction of the vehicle body 210, in other words, captures an image in the direction in which the illumination unit 201 irradiates the notification light, and outputs the image to the image processing means. The image processing means generates image data that can be input to the learning model unit 204 based on the image.

When the image data generated by the image data generation unit 203 is input, the learning model unit 204 uses a machine learning algorithm such as a neural network having predetermined parameters to calculate the safety level indicating the degree of safety of the travel route. A trained model that has been machine-learned to generate a score.

In the machine learning of trained models, a large amount of teacher data is input using a machine learning algorithm such as a neural network as described above. The training data includes data in which a predetermined safety score is associated with image data obtained by photographing a travel route in the workplace 2 . A numerical parameter (in this embodiment, a numerical parameter of 1 to 5) is used as the safety score. Numeric parameters are set by a human or a computer.

For example, if the vehicle is traveling near the rack 3 and there are people on the traveling route, it is determined that the safety is low and the numerical parameter is set to 1. If there is no person but another work vehicle (eg another forklift), set the numeric parameter to 2. If there is neither a person nor another working vehicle, it is determined that the safety is high, and the numerical parameter is set to 3 or more. It can be inferred that there is a certain relationship such as a correlation between the situation of the travel route indicated by the image data and the degree of safety.

The processing unit 205 is configured to acquire a safety score from the learning model unit 204 by inputting the image data acquired from the image data generation unit 203 to the learning model unit 204 . The processing unit 205 outputs the acquired safety score to the map generation unit 207 . Further, the processing unit 205 associates the image data input to the learning model unit 204 with the safety score acquired from the learning model unit 204 to generate image data with a safety score, and generates image data with the safety score. may be transmitted to the management device 100A.

The position estimation unit 206 is configured to recognize the current position (self-position) of the vehicle body 210 and acquire current position information regarding the current position of the vehicle body 210 . In this embodiment, the position estimation unit 206 corresponds to the laser scanner 212 and its computation unit. Position estimation section 206 outputs the acquired current location information to map generation section 207 .

The map generator 207 is configured to store and generate an environment map showing the distribution of safety scores in the workplace 2 . As shown in FIG. 4B, the environment map is a model diagram M2 of the workplace 2 in which a safety score is associated with each predetermined area. Safety scores are updated as appropriate, as described below.

When the safety score is input from the processing unit 205 and the current location information (self-location) is input from the position estimation unit 206, the map generation unit 207 uses the safety score acquired from the processing unit 205 as the current score, The safety score at the self-position within the map is set as the past score, and the current score and the past score are compared. After the comparison, the map generator 207 outputs to the controller 208 the lower safety score (safety score of the smaller numerical parameter).

The map generation unit 207 is configured to update the past score using the current score after outputting the safety score to the control unit 208 . As an update method, the map generation unit 207 may simply replace the current score with the past score, or calculate the average value of the past score for at least one time and the current score, and replace the past score with the average value. good too.

The processing unit 205, the map generation unit 207, and the control unit 208 are configured by, for example, at least one microcomputer, and the processing unit 205, the map generation unit 207, and the control unit 208 are controlled by the CPU of the microcomputer executing a predetermined program. Various functions are realized.

The control unit 208 is configured to adjust the output mode of the notification light and the output state of the alarm sound according to the safety score acquired from the map generation unit 207 . The control unit 208 stores data defining the relationship between the safety score, the notification light, and the alarm sound, as shown in Table 1.

When the numerical parameter of the safety score is 5, the control unit 208 sets the output mode of the notification light of the illumination unit 201 to the constant lighting state, and turns off the alarm sound of the alarm sound output unit 202 . When the numerical parameter of the safety score is in the range of 4 to 2, the control unit 208 sets the output mode of the notification light to a blinking state, and as the numerical parameter of the safety score decreases (safety decreases), Increase blinking speed. When the numerical parameter of the safety score is 1, the control unit 208 turns off the output mode of the notification light and causes the alarm sound output unit 202 to output an alarm sound.

When the control unit 208 changes the output mode of the notification light in the direction in which the numerical parameter of the safety score increases (the safety increases), the control unit 208 prevents frequent changes in the output mode of the notification light. The change may be made after a predetermined time (for example, several seconds) has passed since the change in the output mode.

As described above, in the unmanned forklift 200A according to the present embodiment, the safety score generated in real time based on the image data is the current score, the safety score at the self-position in the environment map is the past score, and the safety score is The output mode of the notification light is changed based on the lower safety score.

For example, when the worker enters a blind spot area (for example, an area where the worker is hidden by the rack 3 or a load and cannot be seen from the photographing means) in an area where the worker frequently works, the past score is higher than the current score. Since the safer score is lower (small numerical parameter score), the unmanned forklift truck 200A changes the output mode of the notification light based on the past score. Therefore, according to the unmanned forklift truck 200A according to the present embodiment, it is possible to appropriately call attention to the worker in the blind spot area.

[Second embodiment]
FIG. 5 shows a block diagram of a cargo handling system 1B according to the second embodiment of the present invention. The cargo handling system 1B includes a management device 100B and at least one laser-guided unmanned forklift 200B (corresponding to the "forklift" of the present invention). The unmanned forklift 200B is the same as the first embodiment except that it does not include the map generator 207. FIG.

The management device 100B manages traveling and cargo handling work of the unmanned forklift 200B. The management device 100B is the same as the first embodiment except that it includes a map generator 104, a collector 105, and a parameter updater .

The map generator 104 has the same configuration as the map generator 207 included in the unmanned forklift 200A of the first embodiment. That is, when the safety score and the current location information (self-position) are input from unmanned forklift 200B, map generation unit 104 uses the safety score obtained from unmanned forklift 200B as the current score, and calculates the safety score at the self-position within the environment map. The sex score is taken as the past score, and the current score and the past score are compared. After the comparison, the map generation unit 104 transmits the safety score of the lower safety (the safety score of the smaller numerical parameter) to the control unit 208 of the unmanned forklift 200B.

The collection unit 105 is configured to collect image data with a safety score from the unmanned forklift 200B and generate learning data that can be input to the parameter update unit 106 based on the image data with the safety score. .

In addition, the collection unit 105 collects image data (image data generated by the image data generation unit 203 and without a safety score) from the unmanned forklift 200B, and associates the safety score with the image data for learning. data may be generated. In this case, learning data can be generated in the same manner as teacher data in the first embodiment. That is, the collection unit 105 uses a numerical parameter (in this embodiment, numerical parameters of 1 to 5) as a safety score, and sets a safety score for each piece of image data. For example, if the vehicle is traveling near the rack 3 and there are people on the traveling route, it is determined that the safety is low and a small numerical parameter is set. On the other hand, when there is no person, it is determined that the safety is high and a large numerical parameter is set. It can be inferred that there is a certain relationship such as a correlation between the situation of the travel route indicated by the image data and the degree of safety.

The parameter updating unit 106 generates update data for updating the parameters of the machine learning algorithm (for example, weighting parameters of the neural network) included in the learning model unit 204 of the unmanned forklift 200B. The parameter updating unit 106 performs machine learning based on learning data using a machine learning algorithm such as a neural network in order to generate update data. Parameter update unit 106 transmits the generated update data to unmanned forklift 200B via communication unit 101 .

The learning model unit 204 of the unmanned forklift 200B updates the parameters of the machine learning algorithm based on the received update data. This allows the learning model unit 204 to generate safety scores based on machine learning algorithms with updated parameters.

[Third embodiment]
FIG. 6 shows a block diagram of a cargo handling system 1C according to the third embodiment of the present invention. The cargo handling system 1C includes a management device 100C, a laser-guided unmanned forklift 200C (corresponding to the "forklift" of the present invention), and at least one working vehicle 300C.

The work vehicle 300C, which is a laser-guided unmanned forklift in this embodiment, travels under the control of the management device 100C and estimates its own position (corresponding to the "other vehicle position" of the present invention). Any forklift or automated guided vehicle that can

100 C of management apparatuses are common in 1st Embodiment. The unmanned forklift 200B is the same as the first embodiment except that it does not have a map generation unit 207 and instead has an information acquisition unit 209 .

The information acquisition unit 209 is configured to acquire position information regarding the current location (other vehicle position) of the work vehicle 300C. The information acquisition unit 209 acquires position information directly from the work vehicle 300</b>C or indirectly via the management device 100</b>C, and outputs the position information to the processing unit 205 .

The processing unit 205 changes the degree of safety of the safety score acquired from the learning model unit 204 (numerical parameters of 1 to 5 as in the first embodiment) according to the distance between the self position and the position of the other vehicle. and output to the control unit 208 .

In this embodiment, the processing unit 205 determines that the degree of safety (numerical parameter) indicated by the safety score acquired from the learning model unit 204 is equal to or greater than a predetermined first threshold, and the distance between the self position and the position of the other vehicle is If it is equal to or less than a predetermined second threshold, the degree of safety of the safety score is changed and output to the control unit 208 .

The first threshold is set to, for example, the smallest numerical parameter among the safety scores when the working vehicle 300C is not shown in the image captured by the image capturing means. In this embodiment, the first threshold is set to the numerical parameter 3. The second threshold is set to L1[m], for example, as shown in FIG. That is, the processing unit 205 reduces the numerical parameter of the safety score (for example , reduced by 1) and output to the control unit 208 .

In the case of FIG. 7, since the work vehicle 300C is not shown in the image captured by the image capturing means due to the presence of the rack 3, the numerical parameter of the safety score is 3 or more, and the distance L2 [m] between the self position and the other vehicle position is Since it is less than or equal to L1[m], it satisfies the condition for decreasing the numerical parameter of the safety score.

In the unmanned forklift 200C according to the present embodiment, the processing unit 205 changes the numerical parameter of the safety score acquired from the learning model unit 204 according to the distance (L2 in FIG. 7) between the self position and the position of the other vehicle. and outputs it to the control unit 208 , and the control unit 208 changes the output mode of the notification light based on the safety score acquired from the processing unit 205 . As a result, for example, when the work vehicle 300C is traveling near a worker (worker X in FIG. 7) who is in the blind spot area of the photographing means, it is possible to appropriately call attention to the worker. becomes.

[Fourth Embodiment]
FIG. 8 shows a block diagram of a cargo handling system 1D according to the fourth embodiment of the present invention. The cargo handling system 1D includes a management device 100D, a laser-guided unmanned forklift 200D (corresponding to the "forklift" of the present invention), and at least one working vehicle 300D.

The unmanned forklift 200D is the same as the unmanned forklift 200C of the third embodiment except that the information acquisition unit 209 is not provided. The work vehicle 300D may be any forklift or automatic guided vehicle, but in this embodiment, at least one of the work vehicles 300D is a forklift having the same configuration as the unmanned forklift 200D.

The management device 100D is the same as the management device 100C of the third embodiment except that it includes a collection unit 105, a parameter update unit 106, an information acquisition unit 107, and a calculation unit . A collection unit 105 and a parameter update unit 106 are common to those in the second embodiment.

The information acquisition unit 107 is configured to acquire, via the communication unit 101, current location information regarding the current location (self location) of the unmanned forklift 200D and location information regarding the current location (other vehicle location) of the work vehicle 300D.

The calculation unit 108 is configured to calculate the distance (for example, L2 in FIG. 7) between the self position and the position of the other vehicle based on the current location information and the position information acquired by the information acquisition unit 107 . Although FIG. 8 shows the computation unit 108 and the integrated control unit 102 separately, the integrated control unit 102 may have the functions of the computation unit 108 .

The calculation unit 108 transmits the calculated distance to the processing unit 205 of the unmanned forklift 200D via the communication unit 101. FIG. Similar to the third embodiment, the processing unit 205 calculates the degree of safety of the safety score obtained from the learning model unit 204 (this embodiment In the form, numerical parameters 1 to 5) are changed and output to the control unit 208 .

Based on the safety score acquired from the processing unit 205, the control unit 208 changes the output mode of the notification light. As a result, for example, when the work vehicle 300D is traveling near the worker who is in the blind spot area of the photographing means, it is possible to appropriately call the worker's attention.

[Fifth embodiment]
FIG. 9 shows a block diagram of a cargo handling system 1E according to the fifth embodiment of the present invention. The cargo handling system 1E includes a management device 100E and at least one manned forklift 200E (corresponding to the "forklift" of the present invention).

A management device 100E is common to the first embodiment. The management device 100E, for example, communicates with the manned forklift 200E and transmits the cargo handling schedule to the manned forklift 200E.

The manned forklift 200E is a counterbalance type forklift that includes a vehicle body 220, a cargo handling device 221, and a head guard 222 provided on the upper portion of the vehicle body 220, as shown in FIG. The lighting section 201 is attached to the head guard 222 . The cargo handling device 221 includes a mast horizontally movable in front and rear of the vehicle body 220 and a fork vertically movable on the mast.

Referring to FIG. 9 again, manned forklift 200E includes illumination unit 201, alarm sound output unit 202, image data generation unit 203, learning model unit 204, processing unit 205, and control unit 208. An illumination unit 201, an alarm sound output unit 202, an image data generation unit 203, a learning model unit 204, and a processing unit 205 are common to those in the first embodiment.

As shown in FIG. 10, the manned forklift truck 200E may travel with the forks facing the direction opposite to the direction of travel, or may travel with the forks facing the direction of travel. For this reason, the lighting unit 201 includes a first LED light that emits notification light toward the road surface on the opposite side of the fork and a second LED light that emits notification light toward the road surface on the fork side (Fig. 10, not shown). A second LED light may be provided, for example, on the mast.

The photographing means of the image data generating unit 203 includes a first photographing unit for photographing an image in the direction in which the first LED light of the illumination unit 201 irradiates the notification light, and a second LED light of the illumination unit 201 that emits the notification light. and second photographing means for photographing an image in the direction in which the is irradiated. Alternatively, the photographing means of the image data generation unit 203 may be configured to be able to change the photographing direction under the control of the control unit 208 .

The control unit 208 is the same as the first embodiment except that it acquires the safety score from the processing unit 205 . The control unit 208 adjusts the output mode of the notification light and the output state of the alarm sound according to the safety score acquired from the processing unit 205 .

According to the manned forklift truck 200E according to the present embodiment, since the output mode of the notification light is changed based on the safety score indicating the degree of safety of the travel route, it is possible to urge the operator to be more appropriately alerted. becomes possible.

[Modification]
Although the embodiments of the forklift truck and cargo handling system according to the present invention have been described above, the present invention is not limited to the above embodiments.

The forklift of the present invention includes a vehicle body, an image data generation unit that captures an image in the traveling direction of the vehicle body and generates image data, and when image data is input, a machine learning algorithm having a predetermined parameter is used to A learning model section machine-learned to generate a safety score that indicates the degree of safety of the vehicle's driving route, and a process of obtaining a safety score from the learning model section by inputting image data into the learning model section. , a lighting unit that emits notification light toward the road surface in the traveling direction, and a control unit that controls the lighting unit, and the control unit changes the output mode of the notification light based on the safety score. If so, the configuration can be changed as appropriate.

The forklift of the present invention may be an unmanned forklift or a manned forklift. The unmanned forklift is not limited to a laser-guided unmanned forklift, but may be another type of unmanned forklift, or a manned and unmanned forklift capable of switching between manned and unmanned operations. The manned forklift is not limited to the counterbalance type, but may be of the reach type, picking lift, or rack fork type.

The unmanned forklift of the present invention preferably has an autonomous travel mechanism. The autonomous running mechanism includes, for example, a laser guidance mechanism or a SLAM guidance mechanism. As shown in the above embodiment, the laser guidance mechanism is a mechanism for autonomous travel based on the self-position and attitude (attitude angle) specified using a laser scanner and a reflector provided on a wall or the like. . The SLAM guidance mechanism is a mechanism for autonomous travel based on the self-position and attitude specified by SLAM, which estimates the self-position and creates an environment map.

The control unit of the present invention may include a method other than changing the flashing speed of the notification light as a method of changing the output mode of the notification light. For example, the color of the notification light may be changed as shown in Table 2 below, or the flashing speed may be changed as in the above embodiment while changing the color of the notification light.

The collection unit 105 and the parameter update unit 106 according to the second embodiment may be provided in the unmanned forklift 200B instead of the management device 100B. However, from the viewpoint of being able to acquire a large amount of data, it is preferable that the management device 100B include the collection unit 105 and the parameter update unit 106. FIG. The same applies to the fourth embodiment.

1A to 1E Cargo handling system 2 Workplace 3 Rack 4 Reflector 100A to 100E Management device 101 Communication unit 102 Integrated control unit 103 Display unit 104 Map generation unit 105 Collection unit 106 Parameter update unit 107 Information acquisition unit 108 Calculation unit 200A to 200D Unmanned forklift 200E Manned forklift 201 Lighting unit 202 Warning sound output unit 203 Image data generation unit 204 Learning model unit 205 Processing unit 206 Position estimation unit 207 Map generation unit 208 Control unit 209 Information acquisition unit 210, 220 Vehicle body 211, 221 Cargo handling device 212 Laser scanner 222 Head guard 300C, 300D work vehicle

Claims (7)

A forklift that performs cargo handling work in a workshop,
a vehicle body;
an image data generating unit that captures an image of the traveling direction of the vehicle body and generates image data;
a learning model unit that is machine-learned to generate a safety score indicating the degree of safety of a travel route of the vehicle body using a machine learning algorithm having predetermined parameters when the image data is input;
a processing unit that acquires the safety score from the learning model unit by inputting the image data into the learning model unit;
a lighting unit that emits notification light toward the road surface in the traveling direction;
A control unit that controls the lighting unit,
The control unit
A forklift, wherein an output mode of the notification light is changed based on the safety score. a position estimation unit that estimates the self-position;
a map generator that generates an environment map showing the distribution of the safety scores in the workplace;
The map generation unit
The safety score acquired from the processing unit is defined as a current score, the safety score at the self-position within the environment map is defined as a past score, and the current score and the past score are compared to determine which one has the lowest safety score. outputting the safety score of to the control unit;
The control unit
The forklift truck according to claim 1, wherein the output mode of the notification light is changed based on the safety score acquired from the map generator. a position estimation unit that estimates the self-position;
an information acquisition unit that acquires the position of another vehicle related to the position of the work vehicle traveling in the workshop;
with
The processing unit is
changing the degree of safety of the safety score acquired from the learning model unit according to the distance between the self position and the other vehicle position, and outputting the safety score to the control unit;
The control unit
The forklift truck according to claim 1, wherein the output mode of the notification light is changed based on the safety score acquired from the processing unit. A cargo handling system comprising a management device and at least one forklift that performs cargo handling work in a workplace under the management of the management device,
The forklift is
a vehicle body;
an image data generating unit that captures an image of the traveling direction of the vehicle body and generates image data;
a learning model unit that is machine-learned to generate a safety score indicating the degree of safety of a travel route of the vehicle body using a machine learning algorithm having predetermined parameters when the image data is input;
a processing unit that acquires the safety score from the learning model unit by inputting the image data into the learning model unit;
a lighting unit that emits notification light toward the road surface in the traveling direction;
A control unit that controls the lighting unit,
The control unit
A cargo handling system, wherein an output mode of the notification light is changed based on the safety score. The forklift includes a position estimation unit that estimates its own position,
The management device
a communication unit for obtaining the safety score and the self-location from the forklift;
a map generator that generates an environment map showing the distribution of the safety scores in the workplace;
The map generation unit
The safety score obtained from the forklift is used as a current score, the safety score at the self-position of the forklift in the environment map is used as a past score, and the current score and the past score are compared to determine safety. transmitting the lower safety score to the controller of the forklift;
The control unit
5. The cargo handling system according to claim 4, wherein the output mode of the notification light is changed based on the safety score obtained from the map generator. The forklift includes a position estimation unit that estimates its own position,
The management device
an information acquisition unit that acquires the self-position of the forklift and the position of other vehicles related to the position of the work vehicle traveling in the workshop;
a calculation unit that calculates the distance between the self position and the position of the other vehicle;
with
The processing unit is
according to the distance obtained from the calculation unit, changing the degree of safety of the safety score obtained from the learning model unit and outputting it to the control unit;
The control unit
5. The cargo handling system according to claim 4, wherein the output mode of the notification light is changed based on the safety score acquired from the processing unit. The processing unit transmits image data with a safety score, in which the safety score obtained from the learning model unit is associated with the image data input to the learning model unit, to the management device,
The management device
a collection unit that collects the image data with the safety score and generates learning data;
a parameter updating unit that performs machine learning based on the learning data, generates update data for updating the parameters included in the learning model unit, and transmits the update data to the learning model unit;
with
The cargo handling system according to any one of claims 4 to 6, wherein the learning model unit updates the parameters based on the update data.

Images