JP2023070545A - Information processing device, information processing method, and program - Google Patents

Abstract

To make it possible to prevent contact of an object without preparing a sensor to a detection object itself.SOLUTION: An information processing device includes a control unit which executes: a process for storing object position information containing position information of one or more objects detected from sensor data acquired from a sensor for detecting the objects; a process for determining a motion of a specific object on the basis of the stored object position information; a process for predicting whether or not another object will enter in a specific range from the specific object after a prescribed time period on the basis of the motion determination result; and a process for issuing an alarm from a notification device when it is predicted that another object will enter in the specific range.SELECTED DRAWING: Figure 1

Description

The present invention relates to an information processing device, an information processing method, and a program.

At work sites such as construction sites, there are many people and heavy machinery, and there is concern about contact between people and heavy machinery during work.

For example, Patent Literature 1 below discloses an automatic control device for heavy machinery that prevents contact with a worker working in the surrounding area or other heavy machinery when the machinery moves backward.

JP 2019-196122 A

Here, in Patent Literature 1, the distance between a heavy machine and an object is measured by a stereo camera provided on the heavy machine, and the heavy machine is automatically controlled according to the distance. However, in the case of a place such as a work site where workers and heavy machinery of various companies exist, it is difficult to attach sensors to all the heavy machinery and workers who enter and leave the place.

Accordingly, the present invention has been made in view of the above problems, and an object of the present invention is to provide a new and improved sensor that can prevent contact with an object without providing a sensor on the detection target itself. An information processing apparatus, an information processing method, and a program are provided.

In order to solve the above problems, according to one aspect of the present invention, there is provided a process of storing object position information including position information of one or more objects detected from sensor data acquired from a sensor for detecting objects in a storage unit. a process of determining the movement of a specific object based on the stored object position information; and whether or not another object will enter a specific range of the specific object after a predetermined time based on the result of the movement determination. and a process of issuing a warning from a notification device when it is predicted that the other object will enter the specific range.

Determination of the motion may include determination of movement direction and movement speed.

The specific range of the specific object may be a range around the specific object that includes at least a region of the specific object.

The specific range of the specific object may include a height direction.

The case where the other object enters the specific range of the specific object may include the case where the objects come into contact with each other.

The control unit may set the specific range based on at least one of the type of the specific object and work conditions.

The control unit may determine, based on the sensor data, whether the work status of the specific object is stopped, moving, or working.

The predetermined time may be set according to at least one of the type of the specific object and work conditions.

In addition to determining the motion of the specific object, the control unit also determines the motion of the other object, and makes a prediction based on the result of determining the motion of the specific object and the result of determining the motion of the other object. you can go

The sensor may be a camera.

The sensor may be a laser.

The sensor data may include a height direction.

The one or more objects detected from the sensor data may be humans or heavy machinery.

One object and another object are detected from the sensor data, and the control unit predicts whether or not the other object will enter a specific range of the one object after a predetermined time. good too.

In order to solve the above problems, according to another aspect of the present invention, a processor generates object position information including position information of one or more objects detected from sensor data acquired from sensors that detect objects. storing in a storage unit; determining motion of a specific object based on the stored object position information; predicting whether or not the other object will enter the specific range, and issuing a warning from a notification device when predicting that the other object will enter the specific range.

In order to solve the above problems, according to another aspect of the present invention, a computer detects object position information including position information of one or more objects detected from sensor data acquired from a sensor that detects objects. a process of storing in a storage unit; a process of determining motion of a specific object based on the stored object position information; A program for functioning as a control unit that performs a process of predicting whether or not another object will enter the specific range, and a process of issuing a warning from a notification device when it is predicted that the other object will enter the specific range is provided.

As described above, according to the present invention, it is possible to prevent contact with an object without providing a sensor on the detection target itself.

BRIEF DESCRIPTION OF THE DRAWINGS It is a figure explaining the outline|summary of the contact prevention system which concerns on this embodiment. 1 is a block diagram showing a configuration example of an information processing apparatus according to this embodiment; FIG. It is a flowchart which shows an example of the flow of operation processing of the contact prevention system by this embodiment. It is a block diagram which shows the structural example of the information processing apparatus by the modification of this embodiment. It is a flowchart which shows an example of the flow of operation|movement processing of the contact prevention system by the modification of this embodiment. It is a figure explaining the specific example of danger prediction by the modification of this embodiment. It is a block diagram showing an example of hardware constitutions of an information processor concerning this embodiment.

Preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings. In the present specification and drawings, constituent elements having substantially the same functional configuration are denoted by the same reference numerals, thereby omitting redundant description.

<1. Overview>
FIG. 1 is a diagram illustrating an outline of a contact prevention system according to this embodiment. This system prevents contact between people and heavy machinery, between people, or between heavy machinery at work sites such as construction sites and construction sites. "Objects" according to this embodiment include, for example, people and heavy machinery.

As shown in FIG. 1, the object contact prevention system according to the present embodiment includes an information processing device 10, one or more sensor devices 20 (here, as an example, a camera 20a), and one or more notification devices 30 (here, as an example, A speaker 30a) is included. Camera 20a may be installed at the work site. Although the installation location is not particularly limited, for example, it is installed in a place where there is a risk of contact due to a blind spot. Also, the speaker 30a is installed at the same place as the camera 20a, for example.

The information processing device 10 communicates with the camera 20a and the speaker 30a via wireless or wired communication. The information processing device 10 may be installed at the work site in the same manner as the camera 20a and the speaker 30a, may be placed on the cloud, or may be installed in an edge computer or an office where the site manager works. It may be a computer.

The information processing apparatus 10 acquires sensor data (captured image) that detects an object from the camera 20a, detects the object from the captured image, and calculates the position of the object at the work site. For example, in the example shown in FIG. 1, the heavy machinery 40 and the worker 50 are detected from the captured image, and their respective positions are calculated. The information processing apparatus 10 also stores the calculated position information (object position information) of each object. The information processing apparatus 10 also determines the motion of each object based on the stored position information of each object, and predicts the risk of contact with the object based on the motion determination result. In motion determination, determination of moving direction and moving speed of each object may be performed.

For example, when the information processing apparatus 10 predicts that contact will occur after a predetermined time from the moving direction and moving speed of the heavy machinery 40 and the moving direction and moving speed of the worker 50, a warning sound (warning or warning voice) is generated from the speaker 30a. is controlled to emit

As a result, it is possible to prevent workers and heavy machinery from coming into contact with each other based on the data from the sensors installed at the work site without providing sensors to the detection targets themselves, such as the workers and heavy machinery.

The outline of the contact prevention system according to the present embodiment has been described above. Next, a specific configuration of the information processing apparatus 10 according to this embodiment will be sequentially described.

<2. Configuration example>
FIG. 2 is a block diagram showing a configuration example of the information processing apparatus 10 according to this embodiment. As shown in FIG. 2, the information processing apparatus 10 has a communication section 110, a control section 120, and a storage section .

(Communication unit 110)
The communication unit 110 can communicate with an external device by wire or wirelessly to transmit and receive data. Specifically, the communication unit 110 receives sensor data for detecting an object from the sensor device 20 . The communication unit 110 also transmits warning sound data and a control signal for instructing output of the warning sound to the notification device 30 . The communication method is not particularly limited. For example, the communication unit 110 can be connected for communication using Wi-Fi (registered trademark), Bluetooth (registered trademark), a wired or wireless LAN (Local Area Network), or the like. Further, the communication unit 110 may transmit and receive data via a public line network such as the Internet, a telephone line network, a satellite communication network, or a dedicated line network such as an IP-VPN (Internet Protocol-Virtual Private Network). good.

(control unit 120)
The control unit 120 generally controls the operation of the information processing device 10 using hardware such as a CPU (Central Processing Unit) and a RAM (Random Access Memory) built into the information processing device 10 .

Specifically, the control unit 120 according to this embodiment can also function as an object detection unit 121, a coordinate conversion unit 122, a memory processing unit 123, an action determination unit 124, a danger prediction unit 125, and a warning notification processing unit 126. .

The object detection unit 121 detects one or more objects within the detection range (for example, the imaging range) of the sensor device 20 based on the sensor data received from the sensor device 20 . The sensor device 20 may be the camera 20a described with reference to FIG. 1 or a ranging sensor such as LiDAR (Light Detection and Ranging) using laser light. Examples of sensor data include captured images and LiDAR point clouds. Moreover, the sensor data may be stereo camera images. A plurality of sensor devices 20 may be provided. The object detection unit 121 may detect a plurality of objects (one object and another object) based on sensor data received from one sensor device 20, or may detect each sensor data received from a plurality of sensor devices 20. A plurality of objects may be detected based on . Also, the sensor device 20 may include multiple types of sensors such as a camera and LiDAR. The object detection method is not particularly limited, but for example, the object detection unit 121 may detect the object from the background difference of the captured image.

The coordinate conversion unit 122 performs processing (calculation processing) for converting the position of the object detected by the sensor device 20 into the position at the work site. The coordinate conversion unit 122 can use coordinate conversion information pre-stored in the coordinate conversion information storage unit 131 to convert the position coordinates of the work site. For example, the coordinate transformation unit 122 can transform the positions of one or more objects (for example, the heavy machinery 40 and the worker 50) appearing in the captured image into the position coordinates of the work site using the coordinate transformation information. The coordinate conversion unit 122 can convert only the captured image into the position coordinates of the work site using the coordinate conversion information, and can also obtain information indicating the distance between the sensor device 20 and the object (for example, obtained from the LiDAR point cloud). distance information) may be used together. In this embodiment, since the position information of each object can be obtained based on sensor data without using GNSS (Global Navigation Satellite System), it can be applied to places where radio waves from satellites do not reach.

The storage processing unit 123 stores the object detection result in the detection result storage unit 132 of the storage unit 130 . The detection results to be stored include information specifying the object detected by the object detection unit 121 (for example, shape feature amount), position coordinates at the work site calculated by the coordinate conversion unit 122, detection time, and the like.

Based on the detection result of each object stored in the detection result storage unit 132, the motion determination unit 124 determines what kind of motion each object is performing. Specifically, the motion determination unit 124 calculates the moving direction and moving speed of each detected object. The motion determination unit 124 can calculate the movement direction and the movement speed from the position coordinates of the object immediately before (for example, three seconds ago) stored in the detection result storage unit 132 .

The danger prediction unit 125 predicts whether or not a dangerous state will occur based on the motion determination result of the motion determination unit 124 . Specifically, the danger prediction unit 125 predicts that danger will occur when another object enters a specific range of a specific object after a predetermined period of time. A specific range is a range around a specific object that includes at least the region of the object. The specific range may be, for example, a range with a radius of 0.5 m or 1 m from the position of the specific object. The predetermined time can be set in advance, for example 5 seconds. The danger prediction unit 125 can perform danger prediction for a specific object among the one or more detected objects based on the result of motion determination of the object. In this embodiment, contact between objects is included as a case where another object enters a specific range of a specific object. That is, the danger prediction unit 125 can predict a dangerous state in which objects come into contact with each other based on the result of motion determination by the motion determination unit 124 . Specific objects and other objects are assumed to be heavy equipment 40 and workers 50, for example. Contact between objects includes contact between heavy machinery and workers (humans), contact between heavy machinery, and contact between workers. The danger prediction unit 125 can predict danger for each detected object. Further, the risk prediction unit 125 may perform risk prediction based on the result of motion determination of a specific object and the result of motion determination of another object.

The warning notification processing unit 126 issues a warning notification from the notification device 30 when danger is predicted (when another object is predicted to enter a specific range of the object after a predetermined time). The notification device 30 may be the speaker 30a installed at the work site as described above, an alarm device carried by the operator of the heavy equipment 40, the worker 50, or a safety manager at the site. It may be a notification terminal. When an alarm device carried by an operator or a worker issues a warning notification, the warning notification processing unit 126 transmits a control signal instructing a warning notification to an alarm device existing within the detection range of the sensor device 20. can be

(storage unit 130)
The storage unit 130 is implemented by ROM (Read Only Memory), RAM (Random Access Memory), etc., and stores control programs for controlling the operation of the information processing apparatus 10, various parameters, and the like.

Further, the storage unit 130 according to this embodiment has a coordinate transformation information storage unit 131 and a detection result storage unit 132 .

An example of the configuration of the information processing apparatus 10 according to the present embodiment has been described above. Note that the configuration of the information processing apparatus 10 according to this embodiment is not limited to the example shown in FIG. For example, the information processing device 10 may be realized by a plurality of devices. Also, at least part of the functional configuration of the control unit 120 may be implemented by an external device. For example, the functions of the object detection unit 121 and the coordinate conversion unit 122 may be performed by the sensor device 20 . In this case, the position coordinate information of each object at the work site can be transmitted from the sensor device 20 to the information processing device 10 . Further, the information processing device 10 may be a device integrated with the sensor device 20 .

<3. Operation processing>
Next, operation processing of the contact prevention system according to this embodiment will be described with reference to FIG. FIG. 3 is a flow chart showing an example of the flow of operation processing of the contact prevention system according to this embodiment.

As shown in FIG. 3, first, the information processing device 10 acquires sensor data from the sensor device 20 (step S103).

Next, the object detection unit 121 of the information processing device 10 detects one or more objects based on the sensor data (step S106).

Next, the coordinate transformation unit 122 transforms the position of the detected object into position coordinates of the site (step S109).

Next, the storage processing unit 123 stores the detection result of each object in the detection result storage unit 132 (step S112).

Subsequently, the motion determination unit 124 determines the motion of each object based on the detection result stored in the detection result storage unit 132 (step S115).

Next, the risk prediction unit 125 predicts the risk of an object based on the action determination result of each object (step S118).

Then, when danger is predicted, the warning notification processing unit 126 controls the notification device 30 to issue a warning notification (step S121).

An example of the operation processing for contact prevention according to the present embodiment has been described above. Note that the processing shown in FIG. 3 is an example, and the present embodiment is not limited to this.

According to the embodiments described above, even if it is difficult to distribute a device (sensor) that notifies all workers and heavy machinery of the position at a work site where many people and heavy machinery come and go, Since the sensor device 20 is installed on site, there is no need to distribute sensors to workers and heavy machinery. In addition, when workers and heavy machinery must work in close proximity, it is difficult to utilize a system that prevents contact based on distance alone. In this embodiment, danger prediction is performed based on the result of motion determination such as the movement direction and movement speed of the detected object. A warning can be given.

<4. Variation>
Next, a modified example of this embodiment will be described. In the above-described embodiment, the risk of contact is predicted based on the motion determination result of the detected object. The risk of contact can be predicted more accurately. A specific description will be given below with reference to FIGS. 4 to 6. FIG.

(4-1. Configuration example)
FIG. 4 is a block diagram showing a configuration example of an information processing device 10A according to a modification of this embodiment. As shown in FIG. 4, an information processing apparatus 10A according to the modification of the present embodiment has a communication section 110, a control section 120A, and a storage section 130A. Control unit 120A also includes object detection unit 121, coordinate conversion unit 122, storage processing unit 123, motion determination unit 124, danger prediction unit 125A, warning notification processing unit 126, object identification unit 127, and work situation determination unit 128. can also work. Further, the storage unit 130A has a coordinate conversion information storage unit 131, a detection result storage unit 132, and a risk prediction information storage unit 133. Each configuration will be described below, but the description of the configurations with the same reference numerals as described with reference to FIG. 2 will be omitted.

First, the functional configuration of the control section 120A will be described. The object detection unit 121, the coordinate conversion unit 122, the storage processing unit 123, and the motion determination unit 124 are the same as those denoted by the same reference numerals as described with reference to FIG.

The danger prediction unit 125A considers the object type identified by the object identification unit 127 and the work situation of the object determined by the work situation determination unit 128 in addition to the motion determination result by the motion determination unit 124, Predict the danger of contact. The object identification unit 127 analyzes the captured image acquired from the camera 20a to perform object recognition, and identifies the object, that is, specifies the type of the object (human and heavy machinery, type of heavy machinery). Although the identification method is not particularly limited, for example, the type of object recognized from the captured image may be identified using learning data in which the characteristics of the type of person, heavy machinery, and each type of heavy machinery are learned in advance (so-called machine learning). technology). The work status determination unit 128 determines the work status of each object based on sensor data. The working status can be classified into, for example, stopping, working, and moving. When the camera 20a is used as the sensor device 20, the work situation determination unit 128 determines, based on the time-series change of the captured image, that if the detected object as a whole does not change, the part of the object changes during the stop. If so, it can be determined that the object is working (working without moving), and if the entire object changes, it can be determined that it is moving.

Further, the risk prediction unit 125A uses the risk prediction information stored in the risk prediction information storage unit 133 to perform risk prediction. The danger prediction unit 125A predicts whether or not another object will enter a specific range of the object after a predetermined period of time. . Hereinafter, the "specific range" is referred to as the "dangerous range". The information of the danger range according to the present embodiment is included in the danger prediction information that can be stored in advance in the danger prediction information storage unit 133 . The danger prediction information may also include information on a "predetermined time" that serves as a reference for danger prediction. Also, the "dangerous range" and the "predetermined time" differ depending on the object and work situation, and are associated with them. That is, the "dangerous range" may differ depending on the person, the heavy equipment, and the type of heavy equipment. Also, the danger range may differ for the same object depending on whether the object is moving, stationary, or working. The danger prediction unit 125A sets the "danger range" and "predetermined time" of the target object based on the danger prediction information.

In this embodiment, by predicting whether or not another object will enter a different danger range according to more specific information such as people, heavy machinery, types of heavy machinery, and work conditions, danger can be predicted more accurately. can do For example, since the speed of heavy machinery differs depending on the type of heavy machinery, it is possible to widen the danger range in advance for heavy machinery that moves fast. Further, as the dangerous area information, information indicating no dangerous area may be set because it is not dangerous even if a worker approaches the surroundings of a stopped heavy machine.

(4-2. Operation processing)
FIG. 5 is a flow chart showing an example of the flow of operation processing of the contact prevention system according to the modification of this embodiment.

As shown in FIG. 5, first, the information processing device 10 acquires sensor data from the sensor device 20 (step S203).

Next, the object detection unit 121 of the information processing device 10 detects one or more objects based on the sensor data (step S206).

Next, the object identification unit 127 identifies the type of each detected object based on the sensor data (step S209).

Next, the coordinate transformation unit 122 transforms the position of the detected object into position coordinates of the site (step S212).

Next, the storage processing unit 123 stores the detection result of each object in the detection result storage unit 132 (step S215). The detection result also includes object identification information (information indicating the type of object).

Subsequently, the motion determination unit 124 determines the motion of each object based on the detection results stored in the detection result storage unit 132 (step S218).

Next, the work status determination unit 128 determines the work status of each object based on the detection results stored in the detection result storage unit 132 (step S221).

Next, the risk prediction unit 125 predicts the risk of the object based on the motion determination result, type, and work situation of each object (step S224). A specific example of risk prediction will be described later with reference to FIG.

Then, when danger is predicted, the warning notification processing unit 126 controls the notification device 30 to issue a warning notification (step S227). A warning notification may be sent to an object predicted to be dangerous. For example, when a worker is predicted to be at risk of coming into contact with heavy machinery, the warning notification processing unit 126 can control an alarm device carried by the worker to issue a warning notification.

An example of the operation processing for contact prevention according to the present embodiment has been described above. Note that the processing shown in FIG. 5 is an example, and the present embodiment is not limited to this.

(4-3. Concrete example of risk prediction)
Next, a specific example of risk prediction according to this modified example will be described with reference to FIG.

The table shown in FIG. 6 shows what kind of danger prediction is performed according to the type of object (type of specific object), the work situation (specific object), and the opponent object (other object). An example is shown.

For example, if the type of object is "backhoe" (an example of heavy equipment) and the work status is "stopped", there is no danger even if a person or heavy equipment approaches, so the danger range is set for the object. (the information "heavy machine is stopped; no danger zone" is obtained from the "hazard zone information" stored in the danger prediction information storage unit 133), and no risk prediction is made for the object. Also, if the work status of the heavy machinery is "stopped", there is a possibility that no operator is on board the heavy machinery, and it is conceivable that a warning cannot be sent to the operator.

On the other hand, when heavy machinery (backhoes, trucks, etc.) is working or moving, there is a risk of contact with people or other heavy machinery. , 2 m behind) is set, and when it is predicted that the other object will be present in the danger range after a predetermined time (for example, after 2 seconds or 3 seconds), the risk of contact is predicted. As described above, information on the danger range and time used as criteria for danger prediction varies depending on the type of object and the work situation, and can be stored in advance in the danger prediction information storage unit 133 as "hazard prediction information." The warning is not limited to the output of a warning sound from the speaker 30a installed at the work site, and may be given to an operator who is on a heavy machine, for example. Specifically, a warning sound may be output from an alarm device provided in the heavy equipment or an alarm device possessed by an operator who boards the heavy equipment. In this case, the information processing device 10A transmits a control signal instructing reproduction of a warning sound to the alarm device detected from within the detection range of the sensor device 20 . For example, when the information processing device 10A is installed at the same place as the sensor device 20, the alarm can be detected by transmitting a response request signal to the surroundings.

Depending on the type of heavy machinery, it may work in conjunction with or close to other heavy machinery, so as shown in the fourth row of the table shown in FIG. Therefore, if the opponent object is a "heavy machine", no danger range is set for the object, and no danger prediction is made.

In addition, in the table shown in FIG. 6, when the type of object is "person" and the counterpart object is also "person", it is assumed that the person is working nearby. , and an example in which the risk range is not set and the risk prediction is not performed during any of the work, but this modification is not limited to this. When one of the people is working or moving, a danger range may be set and danger prediction may be performed. Further, if both persons are stopped, danger prediction may not be performed without setting the danger range.

Further, as an example, as shown in Table 6, when the type of object is "person" and the counterpart object is "heavy machinery", whether the person is stopped, moving, or working, A danger zone is set. Then, when it is predicted that the heavy machinery will be in the danger zone after a predetermined time (in this case, it is assumed that the heavy machinery is moving or working), a warning notification is issued. As an exception, even if a person is moving or working, danger prediction may not be performed if the opponent object "heavy machinery" is stopped. In this way, danger prediction may be made as appropriate by further considering the type of the counterpart object (another object) and the work situation. In addition, for example, even if a person is moving, if the person is walking around the heavy machinery that is the other object, it is assumed that the person is moving around the heavy machinery to do some work. Exceptionally, danger prediction may not be performed.

<5. Hardware configuration example>
Next, an example of the hardware configuration of the information processing apparatus 10 according to this embodiment will be described. The above operations are realized by cooperation between software and hardware described below.

FIG. 7 is a block diagram showing an example of the hardware configuration of the information processing device 900 according to this embodiment. The information processing device 900 is an example of a hardware configuration applied to the information processing device 10 according to this embodiment.

The information processing device 900 includes a CPU (Central Processing Unit) 901, a ROM (Read Only Memory) 902, a RAM (Random Access Memory) 903, a host bus 904, a bridge 905, an external bus 906, and an interface 907. , an input device 908 , an output device 909 , a storage device 910 , a drive 911 , and a communication device 913 .

The CPU 901 functions as an arithmetic processing device and a control device, and controls general operations within the information processing device 900 according to various programs. Alternatively, the CPU 901 may be a microprocessor. The ROM 902 stores programs, calculation parameters, and the like used by the CPU 901 . The RAM 903 temporarily stores programs used in the execution of the CPU 901, parameters that change as appropriate during the execution, and the like. These are interconnected by a host bus 904 comprising a CPU bus or the like. The cooperation of the CPU 901, the ROM 902, and the RAM 903 implements the control unit 120 of the information processing apparatus 10. FIG.

The host bus 904 is connected via a bridge 905 to an external bus 906 such as a PCI (Peripheral Component Interconnect/Interface) bus. Note that the host bus 904, the bridge 905 and the external bus 906 do not necessarily have to be configured separately, and these functions may be implemented in one bus.

The input device 908 includes input means for the operator to input information, such as a mouse, keyboard, touch panel, button, switch, or microphone, and input control for generating an input signal based on the operator's input and outputting it to the CPU 901. It is composed of circuits, etc. An operator who operates the information processing apparatus 900 can input various data to the information processing apparatus 900 and instruct processing operations by operating the input device 908 .

The output device 909 includes, for example, a CRT (Cathode Ray Tube) display device, a liquid crystal display (LCD) device, an OLED (Organic Light Emitting Diode) device, a display device such as a lamp, and an audio output device such as a speaker.

The storage device 910 is a data storage device. The storage device 910 may include a storage medium, a recording device that records data on the storage medium, a reading device that reads data from the storage medium, a deletion device that deletes data recorded on the storage medium, and the like. The storage device 910 implements the storage unit 130 of the information processing apparatus 10 .

A drive 911 is a storage medium reader/writer and is externally attached to the information processing apparatus 900 . The drive 911 reads information recorded on a removable storage medium 912 such as a magnetic disk, optical disk, magneto-optical disk, or semiconductor memory, and outputs the information to the RAM 903 . Drive 911 can also write information to removable storage medium 912 .

A communication device 913 is a communication interface configured by a communication device or the like for communication. The communication device 913 implements the communication unit 110 of the information processing apparatus 10 .

Note that the hardware configuration of the information processing device 900 is not limited to the configuration shown in FIG. 7 . For example, the information processing apparatus 900 does not need to include the communication device 913 when performing communication via a connected external communication device. Further, the information processing apparatus 900 may not include the input device 908 or the output device 909, for example. Also, for example, part or all of the configuration shown in FIG. 7 may be realized by one or two or more ICs (Integrated Circuits).

<6. Supplement>
Although the preferred embodiments of the present invention have been described in detail above with reference to the accompanying drawings, the present invention is not limited to such examples. It is obvious that a person having ordinary knowledge in the technical field to which the present invention belongs can conceive of various modifications or modifications within the scope of the technical idea described in the claims. It is understood that these also naturally belong to the technical scope of the present invention.

For example, the “specific range” used as a criterion for risk prediction performed by the risk prediction unit 125 may include the height direction. Further, the position coordinates of the object converted by the coordinate conversion unit 122 may include height. For example, 3D-LiDAR is used in the sensor device 20 to measure an object three-dimensionally (the height is included in the sensor data), thereby preventing contact with other objects in the height direction. . For example, it may prevent heavy machinery from coming into contact with overhead objects such as ceilings and gates.

Other objects expected to come into contact with a particular object may also include walls. If the other object is a wall, the motion determination is not performed, and the risk prediction unit 125 determines whether the wall will enter the specific range of the specific object after a predetermined time based on the result of the motion determination of the specific object. Predict whether or not (the occurrence of a dangerous situation). Whether or not another object is a wall may be identified by analysis of the captured image (object recognition), or the position of the wall may be grasped from previously prepared map data of the work site. As a result, the present invention can prevent heavy machinery and workers from coming into contact with the wall.

Also, the risk prediction unit 125 may change the risk prediction criteria based on the current time. For example, the criteria for predicting danger may be changed between daytime hours and nighttime hours. Specifically, for example, if an opponent object enters the danger zone (specified range) ``after 3 seconds'' during the day, it is predicted to be dangerous. Danger may be predicted when an object enters. Also, the danger range may be wider at night than during the day.

Further, there may be multiple sensor devices 20 and multiple notification devices 30 . Further, the information processing apparatus 10 may perform risk prediction for each location based on sensor data transmitted from the sensor devices 20 installed at multiple locations. When danger is predicted, the information processing apparatus 10 controls the notification device 30 existing at the location where the danger is predicted to reproduce a warning sound.

It is also possible to create one or more computer programs for causing hardware such as the CPU, ROM, and RAM built into the information processing device 10 to exhibit the functions of the information processing device 10 . Also provided is a computer-readable storage medium having the one or more computer programs stored thereon.

10, 10A information processing device 110 communication unit 120, 120A control unit 121 object detection unit 122 coordinate conversion unit 123 storage processing unit 124 motion determination unit 125 danger prediction unit 126 warning notification processing unit 127 object identification unit 128 work situation determination unit 130, 130A storage unit 131 coordinate conversion information storage unit 132 detection result storage unit 133 danger prediction information storage unit 20 sensor device 30 notification device 40 heavy machinery 50 worker

Claims (16)

A process of storing object position information including position information of one or more objects detected from sensor data acquired from a sensor that detects an object in a storage unit;
a process of determining a motion of a specific object based on the stored object position information;
a process of predicting whether or not another object will enter a specific range of the specific object after a predetermined time based on the motion determination result;
a process of issuing a warning from a notification device when predicting that the other object will enter the specific range;
An information processing device comprising a control unit that performs 2. The information processing apparatus according to claim 1, wherein determination of said motion includes determination of moving direction and moving speed. 3. The information processing apparatus according to claim 1, wherein said specific range of said specific object is a range around said specific object including at least a region of said specific object. 4. The information processing apparatus according to claim 3, wherein said specific range of said specific object includes a height direction. 5. The information processing apparatus according to any one of claims 1 to 4, wherein the case where said other object enters said specific range of said specific object includes a case where objects come into contact with each other. 6. The information processing apparatus according to claim 1, wherein said control unit sets said specific range based on at least one of the type of said specific object and work status. 7. The information processing apparatus according to claim 6, wherein the control unit determines, based on the sensor data, whether the work status of the specific object is stopped, moving, or working. 8. The information processing apparatus according to any one of claims 1 to 7, wherein said predetermined time is set according to at least one of the type of said specific object and work status. The control unit
In addition to determining the motion of the specific object, determine the motion of the other object,
The information processing apparatus according to any one of claims 1 to 8, wherein prediction is performed based on the motion determination result of the specific object and the motion determination result of the other object. The information processing apparatus according to any one of claims 1 to 9, wherein said sensor is a camera. The information processing device according to any one of claims 1 to 9, wherein said sensor is a laser. The information processing apparatus according to any one of claims 1 to 11, wherein said sensor data includes a height direction. The information processing apparatus according to any one of claims 1 to 12, wherein the one or more objects detected from the sensor data are humans or heavy machinery. One object and another object are detected from the sensor data,
14. The information processing apparatus according to any one of claims 1 to 13, wherein said control unit predicts whether or not said other object will enter a specific range of said one object after a predetermined time. the processor
storing in a storage unit object position information including position information of one or more objects detected from sensor data acquired from a sensor that detects the object;
determining a motion of a particular object based on the stored object position information;
Predicting whether or not another object will enter a specific range of the specific object after a predetermined time based on the motion determination result;
issuing a warning from a notification device when predicting that the other object will enter the specific range;
A method of processing information, comprising: the computer,
A process of storing object position information including position information of one or more objects detected from sensor data acquired from a sensor that detects an object in a storage unit;
a process of determining a motion of a specific object based on the stored object position information;
a process of predicting whether or not another object will enter a specific range of the specific object after a predetermined time based on the motion determination result;
a process of issuing a warning from a notification device when predicting that the other object will enter the specific range;
A program that functions as a control unit that performs

Images