Information processing device, information processing method, and program

Abstract

An information processing device (1) according to the present disclosure comprises an estimation unit (12) that estimates the influence degree indicating the presence of a moving body when the moving body operates.

Description

Information processing device, information processing method, and program

[0001] The present disclosure relates to an information processing device, an information processing method, and a program.

[0002] In recent years, mobile objects, including robots, have been increasingly introduced into various situations. It is expected that collaboration and symbiosis between mobile objects and humans will progress in the future, and mobile objects will become more familiar to people. Therefore, various studies that take the presence of mobile objects into consideration are required. Patent Document 1 discloses a technology for making a mobile robot wait at a specific position when passing through a narrow passage so as not to obstruct the passage of workers or other mobile robots. The technology described in Patent Document 1 makes it possible to prevent the mobile robot from obstructing the passage of workers.

[0003] Japanese Patent Application Laid-Open No. 2023-009850

[0004] When a person and a moving object coexist, if the moving object's presence is too strong, it can be stressful for the person, and conversely, if the moving object does not have a strong presence when assisting the person, the moving object may not be able to properly assist the person. Therefore, in order to properly control the moving object depending on the situation, it is desirable to first grasp the presence of the moving object, but the technology described in Patent Document 1 does not disclose how to grasp the presence of the moving object.

[0005] The present disclosure has been made in view of the above, and aims to provide an information processing device that can grasp the presence of a moving body.

[0006] In order to solve the above-described problems and achieve the object, an information processing device according to the present disclosure includes an estimation unit that estimates an influence level indicating the presence of a moving object when the moving object is operating.

[0007] The information processing device according to the present disclosure has an effect of being able to grasp the presence of a moving body.

[0008] FIG. 1 is a diagram showing an example of the configuration of an information processing system according to the first embodiment; A flowchart showing an example of a processing procedure in an information processing device according to the first embodiment; A diagram showing an example of data acquired by an experiment according to the first embodiment; A diagram showing another example of data acquired by an experiment according to the first embodiment; A diagram showing an example of the configuration of a first estimation unit according to the first embodiment when machine learning is used; A diagram showing an example of a target influence level according to facility information according to the first embodiment; A diagram showing an example of a target influence level according to a person's behavior according to the first embodiment; A diagram showing an example of a change in a person's position according to the first embodiment; A diagram showing an example of a target influence level according to a person's position according to the first embodiment; A diagram showing an example of a plurality of people's behavior according to the first embodiment; FIG. 1 shows an example of seating arrangement in the first embodiment. FIG. 2 shows an example of seat presence information in the first embodiment. FIG. 3 shows an example of target influence level according to human behavior in the first embodiment. FIG. 4 shows an example of reduction in influence level by controlling peripheral devices in the first embodiment. FIG. 5 shows an example of the configuration of a computer system realizing each of the information processing devices in the first embodiment. FIG. 6 shows an example of the configuration of an information processing system according to the second embodiment.

[0009] An information processing device, an information processing method, and a program according to an embodiment will be described in detail below with reference to the accompanying drawings.

[0010] First Embodiment. FIG. 1 is a diagram illustrating an example of a configuration of an information processing system 100 according to an embodiment. The information processing system 100 of this embodiment includes an information processing device 1 and a control target device 2. The information processing device 1 is a control device that estimates the degree of influence when a moving object operates and controls the control target device 2 using the estimated degree of influence. Specifically, the degree of influence when a moving object operates is, for example, the degree of influence on a person or an object when the moving object operates, and is a numerical value that indicates the presence of the moving object. Here, the object may be, for example, another moving object, a structure, furniture, equipment, etc., but is not limited to these. The operation of the moving object may include, for example, movement of the moving object, movement of the moving object other than movement, sound output by the moving object, display by the moving object (a moving object having a display function), etc.

[0011] The mobile body may be, for example, a robot equipped with a movement mechanism, but is not limited thereto, and may be any mobile body capable of moving autonomously or by remote control. If the mobile body is a robot, the robot may be a robot with the function of performing a specific task, such as a transport robot, a cleaning robot, or a guide robot, a robot designed to communicate with people, a multi-function robot with multiple functions, or other robots. Furthermore, the mobile body may be a mobile body equipped with a movement mechanism such as wheels or crawlers and capable of moving on the ground or floor, a mobile body with two or four legs such as a humanoid robot or an animal-like robot, or a robot capable of flying in the air such as an unmanned aerial vehicle (drone). The movement mechanism of the mobile body is not limited to these.

[0012] The control target device 2 is a device controlled by the information processing device 1 to change the influence of a moving object, and may be the moving object itself or a peripheral device around the moving object. Examples of peripheral devices include, but are not limited to, a display, a lighting device, a speaker, etc.

[0013] The information processing device 1 includes an information storage unit 11, an estimation unit 12, a control processing unit 15, an acquisition unit 16, and a reception unit 17. The information storage unit 11 stores various information used in processing in the information processing device 1, such as first information used to estimate a first influence degree (described later) and second information used to estimate a second influence degree (described later).

[0014] The estimation unit 12 estimates the degree of influence when the moving body operates, and outputs the estimated degree of influence, i.e., the estimation result of the degree of influence, to the control processing unit 15. In detail, the estimation unit 12 includes a first estimation unit 13 that estimates a first degree of influence and outputs the estimated first degree of influence to the control processing unit 15, and a second estimation unit 14 that estimates a second degree of influence and outputs the estimated second degree of influence to the control processing unit 15.

[0015] The first influence level indicates the degree of influence a moving object has on its surroundings when it operates. The first influence level is dependent on the moving object and is not dependent on the person or object affected. On the other hand, the second influence level indicates the degree of influence a person or object receives from the moving object. The second influence level is dependent on the person or object affected by the moving object. For example, when a large moving object moving at high speed is present, people are generally more susceptible to the influence of the moving object. As such, the degree of influence of a moving object may depend on the moving object itself. On the other hand, for example, when a stationary moving object enters one's field of vision, some people may feel uncomfortable just because it is in their field of vision, while others may not be particularly bothered by it. Furthermore, when a moving object generates noise while moving or operating, whether or not the noise is bothersome may vary from person to person. As such, even if the same moving object performs the same operation, different people may perceive it differently. The same applies to objects that are affected by a moving object. For example, a desk will not be affected by a moving object passing nearby unless it collides with the desk. However, a display device displaying advertisements around the desk will be affected by a moving object passing nearby, as the advertisement will be obstructed.

[0016] From the above, the estimation unit 12 estimates both the degree of influence dependent on the moving body and the degree of influence dependent on a person or an object. This allows the estimation unit 12 to determine a more appropriate degree of influence than when only one of the degrees of influence is considered. Note that, although an example in which the estimation unit 12 includes both the first estimation unit 13 and the second estimation unit 14 will be described below, the estimation unit 12 may include only one of the first estimation unit 13 and the second estimation unit 14. In other words, it is sufficient for the estimation unit 12 to estimate at least one of the first degree of influence and the second degree of influence.

[0017] Furthermore, the estimation unit 12 may estimate the first influence degree and the second influence degree using the estimation reference information acquired by the acquisition unit 16. The estimation reference information includes, for example, at least one of surrounding area information, facility information, equipment information, attribute information, and status information.

[0018] The surrounding information includes, for example, at least one of first surrounding information indicating information about the surroundings of a moving object and second surrounding information indicating information about the surroundings of a person or an object. For example, the first surrounding information is used when estimating the first influence level, and the second surrounding information is used when estimating the second influence level. The first surrounding information is, for example, information indicating the situation about the surroundings of the moving object, and the second surrounding information is, for example, information indicating the situation about the surroundings of a person or an object. The first surrounding information and the second surrounding information may be static information, dynamic information, i.e., information indicating a state, or a combination thereof.

[0019] The first surrounding information may include, but is not limited to, information indicating at least one of the following: the location of a person or object around the moving body; the speed of a person or object around the moving body; the behavior of a person around the moving body; and the content of a conversation between a person around the moving body. The first surrounding information may also include, for example, at least one of image information obtained by capturing images of the area around the moving body, biometric information of a person around the moving body, and sound information indicating sounds around the moving body. The location of a person or object may be calculated from the image information. Position information indicating a location detected by a position detection device such as a GPS (Global Positioning System) receiver included in a mobile device carried by a person may be transmitted and received by the information processing device 1. The image capture device capturing images of the area around the moving body may be provided on the moving body or may be installed within a facility where the moving body is used. A device such as a microphone detecting sounds around the moving body may be provided on the moving body or may be installed within the facility. The position of a person or object may be indicated by position coordinates, or may be indicated in relation to equipment, structures, etc. within the facility in the estimation target range, which is the range within which the influence of the moving object is estimated, such as sitting at a desk, away from the desk, or outside the room.

[0020] The second surrounding information is generated according to a person or object that may be affected by the moving object, i.e., a person or object that is the subject of evaluation of the influence of the moving object (hereinafter also referred to as the evaluation object). The second surrounding information includes, but is not limited to, information indicating at least one of the following: the location of the moving objects around the evaluation object; the speed of the moving objects around the evaluation object; the operating mode of the moving objects around the evaluation object; the volume (volume) of the sound emitted by the moving objects around the evaluation object; and information on objects (other than the moving objects) around the evaluation object. The second surrounding information may include, for example, at least one of image information obtained by photographing the surroundings of the evaluation object and sound information indicating the sound around the evaluation object. Furthermore, the imaging device that photographs the surroundings of the evaluation object may be attached to the object, attached to a mobile terminal carried by a person, or set up within a facility. A device such as a microphone that detects the sound around the moving object may be attached to the object, attached to a mobile terminal carried by a person, or set up within a facility. Note that, for example, image information photographed by an imaging device installed in a facility may serve as both the first surrounding information and the second surrounding information. In this way, the first peripheral information and the second peripheral information may include the same information.

[0021] The facility information includes, for example, information indicating the type of facility where the mobile object is used, i.e., the facility where the mobile object is located, but is not limited to this. This facility is also a facility where the evaluation target object is located. The facility corresponds, for example, to an estimation target range, which is the range within which the information processing device 1 estimates the influence of the mobile object. Note that the estimation target range is not limited to one independent facility, but may be a part of a facility or a combination of multiple facilities. The facility may be indoors, outdoors, or a combination of indoors and outdoors.

[0022] The facility information is information about facilities in a facility where the mobile object is located. The facility information includes, for example, information indicating at least one of the position and shape of walls and the position and shape of roads. Furthermore, for example, if the facility where the mobile object is used is a hotel, the facility information may include information about events held in a hotel facility such as a lobby, information about elevators in the facility where the mobile object is used, and seat occupancy information in an office or the like. The facility information is not limited to these. Furthermore, the facility information may be image information acquired from a capturing device such as a surveillance camera, or seat reservation information in a workplace operated with a free address system. The facility information and the facility information may be input by an operator or the like, or may be transmitted from another device (not shown).

[0023] The attribute information includes at least one of first attribute information indicating attributes of the moving object and second attribute information indicating attributes of the evaluation target. The first attribute information includes at least one of the type, size, color, shape, etc. of the moving object, but is not limited to these. The first attribute information may be input by an operator or the like, or may be image information obtained by photographing the moving object. When the first attribute information is image information, for example, the acquisition unit 16 or the estimation unit 12 estimates the attributes of the moving object from the image information.

[0024] The second attribute information includes, if the evaluation target is a person, at least one of gender, generation, age, information identifying whether the evaluation target is an adult or a child, personality, etc., and if the evaluation target is an object, it includes, but is not limited to, the type of object, function, etc. For example, the first attribute information is used when estimating the first influence degree, and the second attribute information is used when estimating the second influence degree. The second attribute information may be input by an operator or the like, or may be transmitted from another device (not shown).

[0025] The second attribute information may be image information obtained by photographing the evaluation target, or if the evaluation target is a person, it may be input by the person themselves. When input by the person themselves, for example, when entering a facility, room, etc. where a mobile object is used, the person may input the second attribute information using an input device provided at an entrance or the like, and the acquisition unit 16 of the information processing device 1 may receive the second attribute information from the input device. When the second attribute information is image information obtained by photographing the evaluation target, for example, the acquisition unit 16 or the estimation unit 12 estimates the attributes of the evaluation target from the image information.

[0026] Alternatively, registration information associating facial information of a person's face with information indicating the person's attributes may be stored in advance in the information storage unit 11, and the acquisition unit 16 or the estimation unit 12 may identify the person by performing face recognition processing using the image information and facial information. The acquisition unit 16 or the estimation unit 12 may then acquire second attribute information by extracting attribute information corresponding to the identified person from the registration information. Alternatively, registration information associating identification information of a mobile device such as a smartphone or tablet carried by a person with information indicating the attributes of the corresponding person may be stored in advance in the information storage unit 11, and the acquisition unit 16 of the information processing device 1 may receive, from the mobile device, the identification information of the mobile device and location information indicating the location of the mobile device. In this case, if the acquisition unit 16 or the estimation unit 12 determines, based on the received location information, that the person corresponding to the mobile device is to be an evaluation target, it may extract information indicating the attributes of the person corresponding to the mobile device's identification information from the registration information. For example, if the acquisition unit 16 or the estimation unit 12 determines that the mobile device is present within the estimation target range, it may determine that the person corresponding to the mobile device is to be an evaluation target.

[0027] The status information includes at least one of first status information indicating the status of the moving object and second status information indicating the status of the evaluation object. The first status information includes, but is not limited to, at least one of the following: the operation mode of the moving object (cleaning, talking, transporting, guiding, dancing, etc.), the volume (volume) of the sound generated by the moving object, the color of the moving object (if the moving object has a display and the color can be changed), the movement direction of the moving object, the speed of the moving object, and the movement vector of the moving object. The second status information includes, but is not limited to, at least one of the following: the position of the evaluation object, the type of movement of the evaluation object (working, sleeping, etc.), the speed of the evaluation object, and information indicating the emotion of the evaluation object. The first status information may be image information captured by photographing the moving object, and the second status information may be image information captured by photographing the evaluation object. The first status information may be sound information that is a detection result of a sound generated by the moving object, and the second status information may be sound information that is a detection result of a sound generated by the evaluation object. The first status information is used to estimate the first influence level, and the second status information is used to estimate the second influence level. When the control processing unit 15 manages the operation mode, type of operation, etc. of the mobile object, the first attribute information may be input from the control processing unit 15 to the estimation unit 12. Details of the estimation reference information and the estimation method used by the estimation unit 12 will be described later.

[0028] The control processing unit 15 controls the control-target device 2 using the influence received from the estimation unit 12. In detail, for example, the control processing unit 15 calculates a total influence, which is a comprehensive influence, using the first influence and the second influence received from the estimation unit 12, and generates a control signal for controlling the control-target device 2 so as to bring the total influence closer to a target value (target influence) using the total influence, and outputs the control signal to the control-target device 2. There may be a plurality of control-target devices 2, and in this case, the control processing unit 15 generates a control signal corresponding to each of the plurality of control-target devices 2 and outputs the generated control signal to the corresponding control-target device 2.

[0029] Note that, when the estimation unit 12 estimates only the first influence or only the second influence, the control processing unit 15 does not need to calculate the total influence, and controls the control-target device 2 using the influence (first influence or second influence) received from the estimation unit 12. Furthermore, the control processing unit 15 may calculate the total influence by adding the first influence and the second influence, or may calculate the total influence by weighting and adding the first influence and the second influence, or may calculate the total influence by a method other than these. For example, the control processing unit 15 uses the first influence obtained as a distribution and the second influence obtained as a distribution to add or weight and add the value of the first influence and the value of the second influence corresponding to the same position.

[0030] Furthermore, the control processing unit 15 may control the control target device 2 using control reference information acquired by the acquisition unit 16 in addition to the influence degree received from the estimation unit 12. The control reference information includes, like the estimation reference information described above, at least one of, for example, surrounding information, facility information, equipment information, attribute information, and status information. The estimation reference information and the control reference information may be the same or different, or may partially overlap and the remaining portions may differ. Details of the processing in the control processing unit 15 will be described later.

[0031] The acquisition unit 16 acquires information such as estimation reference information and control reference information. The acquisition unit 16 outputs the acquired estimation reference information to the estimation unit 12 and outputs the acquired control reference information to the control processing unit 15. As described above, the estimation reference information and the control reference information may be input by an operator or transmitted from another device. That is, the acquisition unit 16 may acquire the estimation reference information, the control reference information, and the like by accepting input from an operator or by receiving them from another device.

[0032] The reception unit 17 receives various instructions, such as an instruction to start controlling the impact level. The reception unit 17 may receive instructions by receiving input from an operator, or may receive instructions by receiving instructions from another device.

[0033] Next, the operation of this embodiment will be described. Fig. 2 is a flowchart showing an example of a processing procedure in the information processing device 1 of this embodiment. For example, when the information processing device 1 receives an instruction to start control of the impact level, it starts the processing shown in Fig. 2, but the trigger for starting the processing is not limited to this example.

[0034] 2 , the information processing device 1 estimates a first influence degree using the first information (step S1). Specifically, the first estimation unit 13 estimates the first influence degree using the first information and outputs the estimation result to the control processing unit 15.

[0035] The estimation result of the first influence is, for example, information indicating the influence for each position of the moving body in the estimation target range, i.e., the distribution (planar distribution or spatial distribution) of the first influence. However, the estimation result is not limited to this and may be one or more values ​​(influence values) corresponding to the position of the moving body at that time. The one or more values ​​corresponding to the position of the moving body at that time may be, for example, one influence corresponding to the position of the moving body at that time, or a predetermined number of influences corresponding to the position of the moving body at that time and its surroundings. Whether a distribution is obtained as the estimation result of the first influence or one or more values ​​corresponding to the position of the moving body at that time may be determined depending on the method of calculating the influence and the content of the influence control described below. For example, when both the first influence and the second influence are estimated as the influence, the first estimation unit 13 may output information indicating the distribution of the first influence as the estimation result. Furthermore, for example, when only the first influence is estimated as the influence and the sound generated by the moving body is controlled, the first estimation unit 13 may output one or more values ​​corresponding to the position of the moving body at that time as the estimation result. In addition, the first estimation unit 13 may output information indicating the distribution of the first influence degree to the control processing unit 15, and when the control processing unit 15 controls the controlled device 2, it may use the information indicating the distribution of the first influence degree to determine one or more values ​​corresponding to the position of the moving body at that time, and perform the control described below based on the determined one or more values.

[0036] The first information is, for example, information calculated using data acquired through an experiment to investigate the influence of a moving object, and is information for estimating the first influence. Here, a method for calculating the first information will be described. For example, in an experiment to investigate the influence of a moving object, the influence of the evaluation object is acquired in a state where at least one of the position of the moving object and the position of the evaluation object is different. If the evaluation object is a person, the person determines the influence. If the evaluation object is an object, the state of the object is evaluated by, for example, an operator to determine the influence. This is performed for multiple evaluation objects, and multiple data sets including the positions of the moving object, the positions of the evaluation objects, and the acquired influence are recorded.

[0037] In addition, when various conditions within the estimation target range are uniform, the relative positions between the mobile body and the evaluation target may be recorded instead of recording the positions of the mobile body and the evaluation target as a dataset. For example, the relative position may be expressed by indicating the position of the evaluation target in an XY coordinate system with a predetermined reference point on the mobile body as the origin. The method of expressing the relative position is not limited to this example. Furthermore, when various conditions within the estimation target range are not uniform and the degree of influence varies depending on the absolute positions of the mobile body and the evaluation target, the position of the mobile body and the evaluation target are used instead of the relative position. In this case, it is desirable that the experiment be conducted in the actual estimation target range. When using relative positions as a dataset, the estimation target range and the location of the experiment may be different, but it is desirable that the location of the experiment have various conditions similar to those of the estimation target range. Furthermore, when the mobile body is a flyable mobile body, the positions and relative positions of the mobile body and the evaluation target are expressed in a three-dimensional coordinate system, such as an XYZ coordinate system, rather than a two-dimensional XY coordinate system.

[0038] FIG. 3 is a diagram showing an example of data acquired by an experiment in this embodiment. In the example shown in FIG. 3, #1, #2, #3, etc. indicate the identification information of a person, and indicate the influence felt by each person, i.e., the influence evaluated by each person, for each relative position (the relative position between the moving object and the person). For example, the influence is expressed on a scale of 10 from 1 to 10, and each person participating in the experiment selects an influence from the values ​​from 1 to 10. Note that the quantification of the influence is not limited to the example shown on a scale of 10, and any number of numerical levels may be used. Also, although an example will be described here in which a larger influence value indicates a greater influence, the influence may also be defined such that a smaller influence value indicates a greater influence.

[0039] The first information is calculated using, for example, the influence degrees evaluated by multiple people, as shown in FIG. 3 . Here, an example in which the first estimation unit 13 calculates the first information will be described; however, the calculation of the first information may be performed by another device (not shown). When the other device calculates the first information, the first information calculated by the other device is stored in the information storage unit 11. For example, the acquisition unit 16 may acquire the first information from the other device and store the first information in the information storage unit 11. Alternatively, the acquisition unit 16 may acquire the first information by inputting the first information by an operator, and store the first information in the information storage unit 11. When the first estimation unit 13 calculates the first information, data (dataset) obtained by an experiment is stored in the information storage unit 11, and the first estimation unit 13 calculates the first information using the data stored in the information storage unit 11.

[0040] FIG. 4 is a diagram illustrating another example of data acquired by an experiment in this embodiment. In FIG. 3, the influence level is evaluated by changing the relative position. However, this is not limited to this example. Alternatively, an experiment may be conducted by changing the values ​​of the information used as the estimation reference information. In the example illustrated in FIG. 4, the experiment is conducted by changing the relative position and the loudness (volume) of the sound generated by the moving object, and a person evaluates the influence level for each combination of the relative position and volume. While FIGS. 3 and 4 illustrate the data in a table format for illustrative purposes, the data storage format is not limited to this and may be any format. The estimation reference information is not limited to the loudness of the sound generated by the moving object, and may include, for example, at least one of the moving direction of the moving object and facility information. Furthermore, the estimation reference information may include at least one of the color, size, and operation mode of the moving object.

[0041] For example, when the data shown in FIG. 3 is obtained through an experiment, the first estimation unit 13 generates first information indicating the degree of influence for each relative position. Specifically, for example, the first estimation unit 13 calculates a representative value, such as the average or median, of the degrees of influence evaluated for each relative position. As a result, the representative value of the degree of influence for each relative position is obtained as a planar distribution. For example, a rectangle of a predetermined size is defined as one mesh, and the degree of influence for each mesh is obtained through an experiment. The first estimation unit 13 can obtain the planar distribution of the degree of influence by using the representative value for each mesh as the degree of influence. The first estimation unit 13 may use this planar distribution as the first information. Note that when experimental data is obtained by changing the position in a three-dimensional coordinate system, a spatial distribution is obtained instead of a planar distribution.

[0042] Alternatively, the first estimation unit 13 may use the representative value for each relative position to calculate an approximate expression indicating the degree of influence according to the relative position by regression analysis or the like, and use the approximate expression as the first information. The approximate expression may be a polynomial expression or an expression using a logarithm, an exponent, or the like, and is not particularly limited. The method for calculating the approximate expression is not limited to these examples.

[0043] For example, when the data shown in FIG. 4 is obtained by experiment, the first estimation unit 13 may divide the volume into a plurality of ranges of levels, calculate the first information for each level in the same manner as when using the data shown in FIG. 3 , and store the first information for each level in the information storage unit 11. Alternatively, the first estimation unit 13 may obtain a representative value for each relative position and volume, calculate an approximate formula indicating the degree of influence according to the relative position and volume by regression analysis or the like, and use the approximate formula as the first information. As in the above example, the approximate formula may be a polynomial or a formula using a logarithm, exponent, or the like, and is not particularly limited. The method of calculating the approximate formula is not limited to these examples.

[0044] Alternatively, the first estimation unit 13 may use a certain volume as a reference and calculate, as reference information, information similar to the first information when using the data shown in FIG. 3 described above using data corresponding to the reference volume, and then calculate correction information for volume-based correction. For example, a representative value such as an average or median of the influence obtained through experiments may be calculated for each volume, and for representative values ​​of volumes other than the reference volume, a difference or ratio between the representative value of the reference volume and the calculated difference or ratio may be used as correction information. Alternatively, the first estimation unit 13 may use the representative values ​​for each volume to calculate an approximate equation indicating the influence according to the volume through regression analysis or the like, and use the calculated approximate equation as correction information. Furthermore, the first estimation unit 13 may calculate correction information as common information regardless of the relative position, or may divide the relative position into multiple sections and calculate correction information for each section. The first estimation unit 13 stores the calculated reference information and correction information in the information storage unit 11 as first information.

[0045] In addition, when the position of the moving body and the position of the object to be evaluated are used instead of relative positions, the first estimation unit 13 calculates the first information by calculating the influence for each mesh or an approximate formula, for example, by calculating representative values ​​such as the average value and median of the influence evaluated by each of the positions of the moving body and, similarly, for each position of the object to be evaluated.

[0046] The first estimation unit 13 may also conduct an experiment by changing the position of the mobile object and record a data set in which the positions of the mobile object are associated with the degrees of influence evaluated by people at various positions. In this case, a representative value such as the average or median of the degrees of influence is calculated for each position of the mobile object, thereby calculating a distribution of the degrees of influence according to the positions of the mobile object. The first estimation unit 13 stores the degrees of influence according to the positions of the mobile object as first information in the information storage unit 11.

[0047] 3 and 4 are merely examples, and the present invention is not limited to these examples. Experiments are conducted depending on the information used as the estimation reference information. For example, when the color of a moving object is used as the estimation reference information, experiments are conducted by changing not only the position of the moving object and the position of the evaluation object but also the color of the moving object. First information may be calculated for each color of the moving object, or reference information and correction information for correcting differences due to color may be generated as the first information. The same applies when other information (other types of information) is used as the estimation reference information. Similarly, when multiple types of information are used as the estimation reference information, first information may be calculated for each combination of values ​​of the multiple types of information, or reference information and correction information for each type of information may be calculated as the first information, or an approximation formula indicating the relationship between values ​​of the multiple types of information and the influence may be generated as the first information.

[0048] The first information may also be a trained model generated by machine learning. FIG. 5 is a diagram illustrating a configuration example of the first estimation unit 13 according to the present embodiment when machine learning is used. In the example illustrated in FIG. 5 , the first estimation unit 13 includes a model generation unit 131 and an inference unit 132. The model generation unit 131 generates a trained model, for example, by supervised learning, and stores the generated trained model in the information storage unit 11 as the first information. When estimating the first influence, the inference unit 132 estimates (infers) the first influence using the trained model. The trained model is a trained model for inferring the first influence from a feature, and the feature may be a relative position, a position of a moving body, estimation reference information, or a combination of a relative position, a position of a moving body, and estimation reference information.

[0049] When learning is performed using data obtained by the experiment illustrated in FIG. 3 , for example, the model generation unit 131 generates a trained model through supervised learning using multiple data sets including relative positions and influences (corresponding to the first influences obtained by the experiment) that are ground truth data corresponding to the relative positions. The inference unit 132 inputs the relative positions into the trained model to obtain an estimate of the first influence for each relative position. The inference unit 132 performs the same process for each of the multiple relative positions to obtain a distribution of the first influences.

[0050] Alternatively, when learning is performed using data obtained by the experiment exemplified in Fig. 3 described above, the model generation unit 131 may generate a trained model by supervised learning using multiple data sets including the positions of the moving objects and the distribution of influences that are ground truth data corresponding to the positions. In this case, the inference unit 132 obtains the first distribution of influences by inputting the positions of the moving objects to the trained model.

[0051] Furthermore, when learning is performed using data obtained from the experiment illustrated in FIG. 4 , the model generation unit 131 uses the relative position and estimation reference information (volume in the example illustrated in FIG. 4 ) as feature quantities and generates a trained model through supervised learning using multiple data sets including the feature quantities and corresponding influences, which are ground truth data. The inference unit 132 inputs the relative position and the estimation reference information into the trained model to obtain an estimate of the first influence for each relative position. The inference unit 132 obtains a distribution of the first influences by performing the same process for each of the multiple relative positions.

[0052] Alternatively, when learning is performed using data obtained by the experiment illustrated in Fig. 4, the model generation unit 131 may generate a trained model by supervised learning using multiple data sets including reference information for estimation and influence distributions that are ground truth data corresponding to the reference information for estimation. In this case, the inference unit 132 obtains the first influence distribution by inputting the reference information for estimation to the trained model.

[0053] Examples of machine learning used to generate the trained model include neural networks and support vector machines, but the machine learning algorithm is not limited to these. The specific machine learning methods described above are merely examples and are not limited to these. Machine learning may be performed by any method as long as a trained model for inferring the first influence is generated.

[0054] 5 shows an example in which the first estimation unit 13 includes the model generation unit 131, but the present invention is not limited to this. A learning device separate from the information processing device 1 may include the model generation unit 131, and the learning device may generate the trained model. In this case, the trained model generated by the learning device is stored in the information storage unit 11, and the inference unit 132 of the first estimation unit 13 estimates the first influence degree using the trained model stored in the information storage unit 11.

[0055] In addition, when data is acquired for each relative position, when estimating the first influence degree in the above-mentioned step S1, the first estimation unit 13 can estimate the distribution of the first influence degree centered on the position of the moving body by setting the position of the moving body as the origin of the relative position based on the position (current position) of the moving body. The position of the moving body is acquired from the moving body, for example, as state information. In addition, as shown in FIG. 4, when data is acquired for each volume in the experiment, when estimating the first influence degree in the above-mentioned step S1, the first estimation unit 13 calculates the first influence degree according to the volume using sound information indicating the loudness (volume) of the sound generated by the moving body detected by a sound detector or the like and the first information.

[0056] In addition, when experimental data is obtained using the position of the moving body and the position of the object to be evaluated instead of the relative position, the first estimation unit 13 reads out first information from the information storage unit 11 based on the position of the moving body (current position), and estimates the first influence by setting the read out first information as the first influence.

[0057] In addition, when a first influence degree according to the position of the moving body is stored as first information in the information storage unit 11, the first estimation unit 13 reads out the first information and estimates the first influence degree by setting the read-out first information as the first influence degree.

[0058] For example, the first estimation unit 13 may estimate the first influence without using part of the estimation reference information considered when generating the first information. For example, when generating reference information and correction information corresponding to the color, size, and volume of the moving object by changing the color, size, and volume (the volume of the sound generated by the moving object) of each moving object through experiments, the first estimation unit 13 may correct the reference information using only the correction information related to the color and size. Furthermore, when an approximate formula is calculated as the first information, the first estimation unit 13 may generate an approximate formula that takes into account all of the color, size, and volume, an approximate formula that takes into account two of the color, size, and volume, and an approximate formula that takes into account one of the size and volume, and select the approximate formula to use depending on the type of information to be considered when estimating the second influence. Furthermore, when the first information is a trained model, a trained model that takes into account all of color, size, and volume, a trained model that takes into account two of color, size, and volume, and a trained model that takes into account one of size and volume may be generated, and when estimating the second influence, the trained model to be used may be selected depending on the type of information to be considered. This makes it possible to estimate the first influence that takes into account only the information necessary for estimation, such as obtaining an estimation result that does not take into account the influence of hearing when it is not necessary to consider the influence of hearing.

[0059] Furthermore, when multiple types of moving objects are used, the first information may be generated for each moving object, or for each model of moving object. Furthermore, the moving objects may be grouped according to size, shape, type (drone, humanoid, vehicle, etc.), and the like, and the first information may be generated for each group. Furthermore, when multiple estimation target ranges exist, the first information may be generated for each estimation target range, or for each type of facility (library, hotel, office, etc.).

[0060] Furthermore, when estimating the first influence degree, the first estimation unit 13 may use facility information in addition to the first information, and for a first influence degree corresponding to a position of a moving body that is invisible to people in any position because the moving body is surrounded by fixtures, furniture, etc., the first estimation unit 13 may correct the value calculated using the first information to obtain an estimated result of the first influence degree. Specifically, for a first influence degree corresponding to a position of a moving body that is invisible to people in any position, the first estimation unit 13 may correct the first influence degree to lower the value, for example, by subtracting a predetermined value from the value calculated using the first information or by minimizing the influence degree.

[0061] Returning to the description of FIG. 2 , the information processing device 1 estimates a second influence using the second information (step S2). Specifically, the second estimation unit 14 estimates a second influence for each estimation target of the second influence using the second information and outputs the estimation result to the control processing unit 15. The estimation target is an evaluation target of the estimation target and includes at least one of a person and an object that are targets of influence estimation. The estimation target of the second influence may be specified, for example, by the receiving unit 17 receiving input from an operator. Alternatively, the acquisition unit 16 may acquire image information capturing an estimation target range and output it to the second estimation unit 14. The second estimation unit 14 may identify a person present within the estimation target range using the image information and the above-described registered information, and the identified person may be set as the estimation target. Alternatively, the acquisition unit 16 may acquire location information indicating the location of a mobile device and output it to the second estimation unit 14. The second estimation unit 14 may then determine a person corresponding to a mobile device present within the estimation target range based on the location information as the estimation target. When the evaluation object is another moving object, the acquisition unit 16 or the control processing unit 15 may acquire location information indicating the location of the other moving object and output it to the second estimation unit 14, and the second estimation unit 14 may determine the moving object present within the estimation target range based on the location information as the estimation object. When the estimation object is an object other than a moving object, the estimation object may be determined in advance, or may be specified by the reception unit 17 receiving input from an operator, or an object present within the estimation target range may be determined as the estimation object based on image information.

[0062] Like the first influence estimation result, the second influence estimation result may be, for example, information indicating the influence for each position of the estimation object in the estimation target range, i.e., the distribution (planar distribution or spatial distribution) of the second influence. However, the second influence estimation result is not limited to this and may be one or more values ​​(influence values) corresponding to the position of the estimation object at that time. For example, when both the first influence and the second influence are estimated as influences, the second estimation unit 14 may output information indicating the distribution of the second influence as the estimation result. Furthermore, for example, when only the second influence is estimated as the influence and the sound generated by the moving object is controlled, the second estimation unit 14 may output one or more values ​​corresponding to the position of the estimation object at that time as the estimation result. Furthermore, the second estimation unit 14 may output information indicating the distribution of the second influence to the control processing unit 15, and the control processing unit 15 may use the information indicating the distribution of the second influence to determine one or more values ​​corresponding to the position of the estimation object at that time during control, and perform the control described below based on the determined one or more values.

[0063] The second information, like the first information, is information calculated using data obtained by, for example, an experiment to investigate the influence of a moving object, and is information for estimating the second influence. This experiment may be the same as the experiment conducted to calculate the first information, or may be conducted separately from the experiment conducted to calculate the first information.

[0064] Here, an example will be described in which an experiment conducted to calculate the first information also serves as an experiment to calculate the second information. In the calculation of the first information, the first information is calculated without distinguishing between individuals. In the calculation of the second information, the second information is generated while distinguishing between individuals, i.e., for each evaluation object. When relative positions are used to calculate the distribution of the second influence, the basis for the relative positions is a person instead of a moving object. Furthermore, a distribution according to the position of the evaluation object instead of the relative positions may be calculated as the second information.

[0065] For example, as the second information, a representative value for each mesh may be calculated, similar to the first information. In this case, the second estimation unit 14 divides the data for each evaluation object and generates the second information for each evaluation object. Similarly to the first information, the second information may be a distribution indicating the second influence degree for each mesh, or an approximate formula. Similarly to the first information, the second information may be a trained model generated by machine learning. In this case, for example, the second estimation unit 14 may include a model generation unit and an inference unit, similar to the first estimation unit 13 shown in FIG. 5 , or a learning device including the model generation unit may be provided separately from the information processing device 1. When the learning device including the model generation unit is provided separately from the information processing device 1, the trained model generated by the learning device is stored in the information storage unit 11.

[0066] For example, the model generation unit of the second estimation unit 14 generates a trained model for each evaluation object using data corresponding to the evaluation object, similar to the model generation unit 131, and the inference unit of the second estimation unit 14 infers the second impact level using the trained model corresponding to the estimation object when estimating the second impact level. Alternatively, the model generation unit of the second estimation unit 14 may perform training by including identification information that identifies the evaluation object in the feature, and the inference unit of the second estimation unit 14 may estimate the second impact level by including the identification information that identifies the estimation object in the feature and inputting it into the trained model.

[0067] Furthermore, similar to the case of estimating the first influence, the second estimation unit 14 may estimate the second influence without using part of the estimation reference information considered when generating the second information. In the above example, the second information is generated for each evaluation object. However, the evaluation objects may be divided into groups, and the second information may be generated for each group. The index used for grouping may be, for example, an attribute of the evaluation object. That is, for example, if the evaluation objects are people, the evaluation objects may be divided into groups based on at least one of gender, age, personality, and the like, and the second information may be generated for each group. Furthermore, when a trained model is used as the second information, learning may be performed by including the attributes of each group in the feature, and the inference unit of the second estimation unit 14 may estimate the second influence by inputting the attribute of the estimation object into the trained model, including the feature.

[0068] Furthermore, when estimating the second influence, the second estimation unit 14 may correct the value calculated using the second information for the second influence corresponding to the position of the estimation object where the moving body is not visible due to fixtures, furniture, walls, etc. being between the moving body and the person who is the estimation object, to obtain the estimated result of the second influence. Specifically, the second estimation unit 14 identifies the estimation object corresponding to the position of the estimation object where the moving body is not visible, using the position of the moving body, the position of the estimation object, and at least one of equipment information and facility information in addition to the second information. Then, the second estimation unit 14 may correct the second influence of the identified estimation object to reduce the value, for example, by subtracting a predetermined value from the value calculated using the second information or by minimizing the second influence.

[0069] After step S2, the information processing device 1 determines whether to implement control (step S3). In detail, for example, the control processing unit 15 determines not to implement control of the control-target device 2 if the impact is within the range of the target impact. On the other hand, the control processing unit 15 determines to implement control of the control-target device 2 if the impact is expected to deviate from the target impact range within a certain time. The control of the control-target device 2 is control for changing the impact. The certain time may be 0 (0 hours). That is, the control processing unit 15 may determine to implement control for changing the impact if the impact deviates from the target impact range. The certain time is set appropriately based on the type of moving object, the content of the control for changing the impact, etc. The certain time may be the control period or a time longer than the control period. If the certain time is not 0, the estimation unit 12 estimates the impact for the certain time ahead. The impact may be a first impact, a second impact, or a total impact calculated by the control processing unit 15 from the first impact and the second impact.

[0070] The target influence level may be determined in advance and held by the control processing unit 15. Alternatively, the target influence level may be stored in the information storage unit 11 and read out by the control processing unit 15 from the information storage unit 11. The target influence level may be determined according to control reference information, as will be described later. That is, the control processing unit 15 may perform control based on the control reference information. For example, the target influence level may be determined according to peripheral information. It is assumed that the mobile object performs an operation autonomously or by remote control, separate from the control of the influence level. The operation of the mobile object may be work such as cleaning or transportation, or may be, but is not limited to, a conversation with a person. Details of the target influence level will be described later.

[0071] If it is determined that control will not be performed (step S3: No), the information processing device 1 terminates the processing. If it is determined that control will be performed (step S3: Yes), the information processing device 1 controls the control-target device 2 to change the degree of influence (step S4), and terminates the processing. In detail, the control processing unit 15 generates a control signal for changing the degree of influence so that the degree of influence becomes the target degree of influence, and transmits the generated control signal to the control-target device 2. The degree of influence is changed by, for example, at least one of moving the position of the moving object, changing the volume of the moving object, displaying on a display, outputting sound from a speaker, turning on or off lighting by a lighting device, etc.

[0072] The information processing device 1 performs the process shown in FIG. 2 at, for example, a predetermined control cycle. This allows the information processing device 1 to grasp the presence of a moving object. Furthermore, when the degree of influence on the evaluation object deviates from the target degree of influence, the information processing device 1 controls the degree of influence on the evaluation object to be within the range of the target degree of influence. This allows the degree of influence of the moving object to be adjusted according to the situation. For example, the information processing device 1 sets a low upper limit of the target degree of influence in a situation where people are concerned about the presence of the moving object, and sets a high lower limit of the influence in a situation where it is better for the moving object to be noticeable. This allows the information processing device 1 to lower the target degree of influence in a situation where people are concerned about the presence of the moving object, and to raise the target degree of influence in a situation where it is better for the moving object to be noticeable.

[0073] 2, the influence degree is controlled after the estimation of the first influence degree and the estimation of the second influence degree, but the influence degree does not have to be controlled. Even in this case, the influence degree can be estimated, thereby achieving the effect of being able to grasp the presence of a moving object.

[0074] 2, an example has been described in which the control processing unit 15 performs control to change the impact degree when the estimated impact degree deviates from the target impact degree, but this is not limiting, and the control processing unit 15 may control the control target device 2 so that the impact degree satisfies a predetermined condition based on the estimated impact degree. The predetermined condition may be a condition that the impact degree is within a range of the target impact degree, or a condition that the impact degree is minimized or maximized.

[0075] Specific examples of influence control in the information processing device 1 are described below. For example, the target influence may be set to a threshold value or less regardless of the situation. In this case, for example, the control processing unit 15 of the information processing device 1 uses the estimated influence and performs control to reduce the influence when the estimated influence exceeds the threshold. Examples of control to reduce the influence include changing the position of the moving object, changing the operation mode of the moving object, changing the moving route of the moving object to move on a smooth floor surface that is less likely to generate noise, reducing the volume of sound emitted by the moving object, and controlling peripheral devices near the moving object to draw a person's attention to the peripheral devices. The type of control to be performed to reduce the influence may be determined in advance or may be determined based on the control reference information described above. For example, the type of control to be performed may be determined in advance depending on the type of moving object, and the control processing unit 15 may determine the content of the control based on the type of moving object. Furthermore, for example, the type of control to be performed may be determined in advance based on the type of behavior of the estimated object, and the control processing unit 15 may estimate the behavior of the estimated object based on image information obtained by capturing the estimated object and determine the content of the control based on the estimated behavior.

[0076] Furthermore, the control processing unit 15 of the information processing device 1 is not limited to the control of changing the influence degree, and may also control the moving object using the influence degree. For example, when determining a route for moving the moving object, the route may be determined so as to be a route with a low influence degree, for example, a route with an influence degree equal to or less than a threshold value.

[0077] Furthermore, for example, the target influence level may be set according to facility information indicating the type of facility corresponding to the estimation target range. FIG. 6 is a diagram showing an example of the target influence level according to facility information in this embodiment. In the example shown in FIG. 6, for example, if the facility is a library, the target influence level is 2 or less, if the facility is a supermarket, the target influence level is 5 or more, and if the facility is a high-end restaurant, the target influence level is 3 or less. For example, in libraries, high-end restaurants, etc., it is preferable for the moving object to be inconspicuous, while in supermarkets, it may be desirable for the moving object to be conspicuous. In such cases, for example, by setting the target influence level according to the type of facility as shown in FIG. 6, the presence of the moving object can be adjusted according to the facility.

[0078] The target influence level may also be set according to surrounding information. FIG. 7 is a diagram showing an example of a target influence level according to a person's behavior in this embodiment. In the example shown in FIG. 7, information indicating a person's behavior is used as an example of surrounding information. In the example shown in FIG. 7, when a person in the vicinity of the moving object is working or studying, the target influence level is set low, and when the person is walking, the upper limit of the target influence level is set higher than when the person is working or studying. This reduces the possibility that the moving object will affect a person who is concentrating on work or study. Note that, for example, the control processing unit 15 can determine a person's behavior using image information of a person.

[0079] Furthermore, the target influence level may be set according to the position of the person. Fig. 8 is a diagram showing an example of a change in the position of person 4 in this embodiment. The top row of Fig. 8 shows a state in which person 4, who is present in the vicinity of moving object 3, is sitting at a desk and working, the middle row shows a state in which person 4 has left the desk and started walking, and the bottom row shows a state in which person 4 has left the room.

[0080] FIG. 9 is a diagram illustrating an example of a target influence level according to the position of person 4 in this embodiment. The example illustrated in FIG. 9 shows a target influence level when moving object 3 is inside a room, and the target influence level is set depending on whether person 4 is sitting at a desk, in a room away from the desk, or outside the room. For example, when person 4 is sitting at a desk near the moving object, the target influence level is set low because person 4 is likely working, studying, or the like. When person 4 is in a room away from the desk, the upper limit of the target influence level is set higher than when person 4 is sitting at a desk. Furthermore, when person 4 is outside the room, the upper limit of the target influence level is set higher than when person 4 is in a room away from the desk. As a result, for example, as shown in the upper part of FIG. 8 , when person 4 is working, the target influence level of moving object 3 can be reduced by lowering the target influence level. Furthermore, for example, it is assumed that the control of the influence level includes stopping a specified action, room cleaning is specified as the action of moving object 3, and the influence level in the room cleaning action mode exceeds the target influence level. In this case, the control processing unit 15 may transmit a control signal to the moving object 3 to stop cleaning when the person 4 is in the room, based on the degree of influence, and may transmit a control signal to cancel the stop of cleaning when the person 4 leaves the room. This allows the control processing unit 15 to stop cleaning by the moving object 3 when a person is in the room, and to have the moving object 3 perform cleaning when the person leaves the room.

[0081] The target influence level may also be set based on facility information, surrounding area information, and attribute information. For example, if the facility information is a hotel, the location of the person 4 around the mobile object 3 is within a certain distance from the mobile object 3, and the attribute information includes the attribute of the person 4 around the mobile object 3 as a guest, the target influence level may be set to a minimum value. In this case, the control to reduce the influence level may be set to move the mobile object 3 to a predetermined location that is invisible to the guests. This allows the mobile object 3 to be moved to a location that is invisible to the hotel guests. The location of the person 4 around the mobile object 3 is included in the surrounding area information, as described above. In this example, the attribute information includes whether the person 4 is a guest. However, for employees other than guests, for example, the face information described above can be registered to determine whether the person 4 is a guest or an employee. Then, for example, the acquisition unit 16 or the control processing unit 15 determines whether the person 4 is an employee based on the image information and face information of the person 4, and if it is determined that the person 4 is not an employee, the acquisition unit 16 or the control processing unit 15 determines that the person 4 is a guest.

[0082] Alternatively, the target influence level corresponding to studying or working may be set low as in the example shown in FIG. 7 , and when walking while looking at a smartphone, the target influence level may be set to a certain value or higher, such as 5 or higher, to increase the influence level. For example, the control processing unit 15 may increase the influence level by transmitting a control signal to the moving object 3 instructing the moving object 3 to talk to the person 4. This allows the person 4 to pay attention to the moving object 3 when walking while looking at a smartphone. Note that the control processing unit 15 may also increase the influence level when the person 4 is looking away, not limited to the example of the person 4 walking while looking at a smartphone. That is, the control processing unit 15 may increase the influence level when it determines that the person 4 is looking away based on image information obtained by capturing an image of the surroundings of the moving object 3. For example, the control processing unit 15 may use image information to determine the head direction, face direction, and whether the person 4 is walking, and determine that the person 4 is looking away when it determines that the head direction is the same as the walking direction but the face is facing downward.

[0083] 10 is a diagram showing an example of the behavior of multiple people according to this embodiment. For example, as shown in the upper part of FIG. 10, assume that both person 4-1, who is studying or working, and person 4-2, who is walking while looking at their smartphone, are present around moving object 3. In this case, priority may be given to controlling the influence on person 4-1, and as shown in the lower part of FIG. 10, once person 4-2 moves away from person 4-1, a control signal may be transmitted to moving object 3 to generate a sound to call attention or to instruct person 4-2 to talk to person 4-2.

[0084] Furthermore, as an example of human behavior, the target influence level may be set according to the content of a person's conversation. FIG. 11 is a diagram illustrating an example of the target influence level according to the content of a conversation according to this embodiment. As shown in FIG. 11 , when a conversation includes words (keywords) related to work content, the target influence level is set low. When a conversation includes words related to leisure, the upper limit of the target influence level is set higher than when the conversation includes words related to work content. The target influence level may also be set low when there is no conversation. Words related to work content include, but are not limited to, "business," "mass production," and "profit," and are determined in advance. Leisure-related words are also determined in advance. Note that the specific content of the words related to work content and the words related to leisure may be determined according to the facility in question or may be changeable by the operator. In this way, when an unsafe situation is predicted due to contact between the moving object 3 and the person 4, the control processing unit 15 may perform control to increase the influence level.

[0085] Furthermore, the control processing unit 15 may grasp the position of a person according to facility information and control the influence. For example, a first influence for each relative position is estimated as the influence, and the closer to the moving object the higher the influence. The target influence is set to a threshold value or less. The facility information includes information indicating the layout of seats within the facility and seat occupancy information indicating whether a person is seated. In such a case, instead of using the target influence, the control processing unit 15 may perform control so as to reduce the total influence on multiple people or objects.

[0086] FIG. 12 is a diagram showing an example of seating arrangement in this embodiment. In the example shown in FIG. 12, six desks, A-1 to A-3 and B-1 to B-3, each have four seats. In FIG. 12, empty seats are indicated by white shapes, and occupied seats are indicated by black hatched shapes. FIG. 13 is a diagram showing an example of seating information in this embodiment. In the example shown in FIG. 13, the seating information includes the number of people seated at each desk, i.e., the number of people present. The seating information shown in FIG. 13 corresponds to the state shown in FIG. 12. The seating information may be generated from image information captured by a photographing device, or may be generated based on reservation information indicating seat reservations. For example, a management device that manages the facility manages the reservation information, and the information processing device 1 acquires the reservation information from the management device. Alternatively, the acquisition unit 16 or the control processing unit 15 in the information processing device 1 may calculate the number of people present from the image information.

[0087] 12, assume that the mobile unit 3 has been instructed to move to destination 5 via route R1. In this case, the control processing unit 15 may determine that route R2, which passes near the occupied desk A-3 and the unoccupied desks A-1, A-2, and B-1, will have a lower impact on all occupants than route R1, which passes near the occupied desks A-3, B-2, and B-3 and the unoccupied desk B-1, and transmit a control signal to the mobile unit 3 instructing it to change route R1 to route R2. Furthermore, in the example shown in FIG. 13, the seating information indicates the number of occupants per desk, but the seating information may also indicate whether each seat is occupied.

[0088] The control processing unit 15 may also perform control to change the influence level taking into account the gaze direction of the person. FIG. 14 is a diagram for explaining control that takes gaze direction into account according to this embodiment. For example, the control processing unit 15 may estimate the gaze direction 52 of the person from image information captured by the imaging device 51, which is obtained as peripheral information, and, if the moving object 3 is located in the estimated gaze direction 52, change the position of the moving object 3 to reduce the influence level on the person. The control processing unit 15 may perform this control based on the gaze direction in addition to control using the influence level estimated by the estimation unit 12, or may perform this control based on the gaze direction alone. In the example shown in FIG. 14, the moving object 3 is located on an extension of the gaze direction 52 of the person sitting in the seat at the bottom left of desk B-3. Therefore, the control processing unit 15 may transmit a control signal to the moving object 3 instructing it to move to the left. Furthermore, Figure 14 shows an example in which control is performed to prevent the moving body from entering the field of view of a seated person, but this is not limited to this. The control processing unit 15 may also control the moving body 3 so that it does not enter the field of view based on the line of sight of a walking person, a standing person, etc.

[0089] For example, suppose the facility is a hotel, and the target influence level for the hotel is set low in the target influence level according to the facility information as illustrated in Fig. 6, thereby controlling the moving object 3 so that it is less likely to be noticed by guests. Furthermore, suppose the facility information for the facility includes event information indicating a schedule of events in the lobby. In this case, during times when a glamorous event, such as a piano performance or a lively event, is being held in the lobby, the control processing unit 15 may control the moving object 3 to pass through the lobby by raising the upper limit of the target influence level.

[0090] Furthermore, while FIG. 7 illustrates an example of setting a target influence level for each human behavior, the human behavior is not limited to examples of a person being active and may include states such as sleeping and poor health. FIG. 15 illustrates another example of target influence levels according to human behavior in this embodiment. A human behavior is determined, for example, by the acquisition unit 16 or the control processing unit 15 using image information. As illustrated in FIG. 15 , the target influence level may be set high, for example, when a person loses an item, such as by setting the target influence level to a certain value or higher. This makes it easier for the person to notice the lost item. Similarly, the target influence level may be set high, for example, when a person is feeling unwell, such as by setting the target influence level to a certain value or higher. This makes it easier for people around the person to notice that they are feeling unwell. Furthermore, when a person is sleeping, the target influence level may be set below a threshold value to lower the target influence level and not disturb their sleep. Note that, if vital data can be acquired from a person's mobile device, the determination of whether or not the person is feeling unwell or whether or not the person is sleeping may be performed based on vital data.

[0091] 15, the target influence level may be set high, for example, to a certain value or more when a person's behavior is suspicious. For example, by defining the content of control corresponding to suspicious behavior as turning on lighting devices around the moving object 3 or turning on lighting devices provided on the moving object 3, having the moving object 3 talk to people, or having the moving object 3 emit a sound, the presence of the moving object 3 is made more noticeable, thereby making it possible to deter people who behave suspiciously.

[0092] Furthermore, as a control to reduce the influence level, the control processing unit 15 may generate a control signal for displaying an image on a display, which is a peripheral device, and transmit the generated control signal to the display. FIG. 16 is a diagram for explaining the reduction in influence level by controlling a peripheral device in this embodiment. For example, when a person 4 approaches a moving object 3 by passing by the person 4, if the influence level is expected to deviate from the target influence level due to the person 4's proximity to the moving object 3, the control processing unit 15 generates a control signal for displaying an image on the display 6 and transmits the generated control signal to the display 6. Note that the image referred to here includes not only still images but also moving images. As a result, the image is displayed on the display 6, and the person 4 looks at the display 6, thereby reducing the influence level of the moving object 3 on the person 4.

[0093] Note that control of displaying an image on the display 6 is an example of control for changing the influence level, and the specific content of the control may be determined in advance through experiments, for example. For example, experiments may be conducted in various cases, such as displaying an image on the display 6 or outputting audio from a speaker, to evaluate changes in the influence level, and effective measures may be determined as control for reducing the influence level. Even if the same image is displayed on the display 6, whether or not the influence level of the moving object 3 changes may vary depending on the person 4, and the images (image content) that interest each person 4 may also vary. Therefore, effective control content may be determined in advance for each person 4. Furthermore, the content of the image to be displayed may be determined for each person 4. Instead of for each person 4, people 4 may be grouped by attribute, and control content, image content, etc. may be determined for each group. In this way, when it is determined to reduce the influence level based on the estimation result of the estimation unit 12, the control processing unit 15 may display an image on the display 6 and determine the image to be displayed based on the second attribute information.

[0094] Next, the hardware configuration of the information processing device 1 of this embodiment will be described. In the information processing device 1 of this embodiment, a computer program describing the processing of each of the information processing devices 1 is executed on a computer system, causing each computer system to function as the information processing device 1. FIG. 17 is a diagram showing an example configuration of a computer system that realizes each of the information processing devices 1 of this embodiment. As shown in FIG. 17, this computer system includes a control unit 101, an input unit 102, a storage unit 103, a display unit 104, a communication unit 105, and an output unit 106, which are connected via a system bus 107.

[0095] In FIG. 17 , the control unit 101 is a processor such as a CPU (Central Processing Unit) and executes a program describing the processes performed by the information processing device 1 of this embodiment. The input unit 102 is composed of, for example, a keyboard, buttons, a mouse, and the like, and is used by a user of the computer system to input various information. The memory unit 103 includes various memories such as RAM (Random Access Memory) and ROM (Read Only Memory) and a storage device such as a hard disk, and stores programs to be executed by the control unit 101, necessary data obtained during processing, and the like. The memory unit 103 is also used as a temporary storage area for programs. The control unit 101 and the memory unit 103, for example, constitute a processing circuit. The processing circuit may be a single circuit or multiple circuits. The display unit 104 is composed of a display, an LCD (Liquid Crystal Display), and the like, and displays various screens to the user of the computer system. Note that a touch panel in which the input unit 102 and the display unit 104 are integrated may also be used. The communication unit 105 is a receiver and transmitter that perform communication processing. The output unit 106 is a speaker or the like. Note that Fig. 17 is just an example, and the configuration of the computer system that realizes each of the information processing devices 1 is not limited to the example shown in Fig. 17. For example, the output unit 106 may not be provided.

[0096] Here, an example of the operation of the computer system until the program of this embodiment is ready to be executed will be described. In the computer system having the above-described configuration, for example, the program is installed in storage unit 103 from a CD-ROM or DVD-ROM inserted in a CD (Compact Disc)-ROM drive or DVD (Digital Versatile Disc)-ROM drive (not shown). Then, when the program is executed, the program read from storage unit 103 is stored in the main storage area of ​​storage unit 103. In this state, control unit 101 executes the processes as each of information processing device 1 of this embodiment in accordance with the program stored in storage unit 103.

[0097] In the above description, a program describing the processing in each information processing device 1 is provided using a CD-ROM or DVD-ROM as a recording medium, but this is not limited to this. Depending on the configuration of the computer system, the capacity of the program to be provided, etc., it is also possible to use a program provided via a transmission medium such as the Internet via the communication unit 105.

[0098] The program of this embodiment causes a computer system to execute, for example, an estimation step of estimating the degree of influence when the moving object 3 moves.

[0099] The estimation unit 12 and the control processing unit 15 shown in FIG. 1 are realized by the control unit 101 shown in FIG. 17 executing a program stored in the storage unit 103 shown in FIG. 17. The storage unit 103 is also used to realize the estimation unit 12 and the control processing unit 15. The communication unit 105 shown in FIG. 17 is also used to realize the control processing unit 15. The acquisition unit 16 and the reception unit 17 shown in FIG. 1 are each realized by at least one of the input unit 102 and the communication unit 105 shown in FIG. 17. Some functions of the acquisition unit 16 may be executed by the control unit 101. The information storage unit 11 shown in FIG. 1 is part of the storage unit 103 shown in FIG. 17. The information processing device 1 may be realized by multiple computer systems. For example, the information processing device 1 may be realized by a cloud computer system.

[0100] As described above, the information processing device 1 of the present embodiment estimates the degree of influence when the moving object 3 moves. This makes it possible to grasp the presence of the moving object 3. Furthermore, the information processing device 1 uses the estimated degree of influence to perform control so that the degree of influence satisfies a predetermined condition, thereby making it possible to appropriately maintain the degree of influence of the moving object 3.

[0101] Second Embodiment Fig. 18 is a diagram showing an example of the configuration of an information processing system 100a according to a second embodiment. The information processing system 100a according to this embodiment includes an information processing device 1a and a display device 7. Hereinafter, components having the same functions as those in the first embodiment will be assigned the same reference numerals as those in the first embodiment, and redundant explanations will be omitted. Below, differences from the first embodiment will be mainly explained.

[0102] The information processing device 1a of this embodiment is similar to the information processing device 1 of the first embodiment, except that it includes a display information generation unit 18 instead of the control processing unit 15. In this embodiment, the estimation unit 12 outputs the estimation result of the influence to the display information generation unit 18, and the display information generation unit 18 generates display information showing the estimation result received from the estimation unit 12 as a distribution map and outputs the display information to the display device 7. The display information is information for displaying the estimation result of the influence as a distribution map on the display device 7. As a result, the display device 7 displays the distribution map of the estimated influence. In this embodiment as well, the estimation unit 12 estimates at least one of the first influence and the second influence. The distribution map may be a distribution map on a two-dimensional plane or a distribution map in three-dimensional space.

[0103] 19 is a flowchart showing an example of a processing procedure in the information processing device 1a according to this embodiment. The information processing device 1a determines whether a display instruction has been received (step S11). In detail, for example, when the reception unit 17 receives a display instruction input from an operator or the like, or receives a display instruction from another device (not shown), it determines that a display instruction has been received. If a display instruction has not been received (step S11: No), the information processing device 1a repeats step S11.

[0104] If a display instruction has been received (Yes in step S11), the information processing device 1a performs the processes of steps S1 and S2. Steps S1 and S2 are the same as those in the first embodiment. After step S2, the information processing device 1a generates display information (step S12). In detail, the display information generation unit 18 generates display information showing a distribution map of the estimated influence degrees using the estimation results of the influence degrees received from the estimation unit 12.

[0105] Next, the information processing device 1a outputs the display information (step S13) and ends the process. Specifically, in step S13, the display information generation unit 18 outputs the display information to the display device 7. The display device 7 may be a display, a monitor, or a terminal device that is a computer system. In this case, the display instruction may be transmitted from the terminal device, and the reception unit 17 may receive the display instruction from the terminal device.

[0106] 20 to 22 are diagrams showing examples of display screens displayed on the display device 7 of this embodiment. In Fig. 20 to 22, the distribution of the estimated influence degree on a two-dimensional plane is shown as a contour diagram, but the display format of the distribution diagram is not limited to the examples shown in Fig. 20 to 22.

[0107] FIG. 20 shows an example in which a diagram showing a distribution 32 of the first influence estimation result is displayed as a distribution diagram of the influence estimation result. In the example shown in FIG. 20, the influence is widely distributed in the movement direction 31 of the moving object 3. For example, an experiment may be conducted while changing the movement direction to estimate the influence taking into account the influence of the movement direction. Alternatively, for example, the display information generation unit 18 may generate a distribution diagram such as that shown in FIG. 20 by taking into account the movement from the current processing timing to the next processing timing for each processing cycle and overlaying the distribution of the influence for each time period during that time. In this case, instead of adding the influences directly, the values ​​of the influences may be normalized by, for example, multiplying them by the time interval and then adding them.

[0108] 21 shows an example in which a diagram showing a distribution 41 of the estimation results of the second influence is displayed as a distribution diagram of the estimation results of the influence. In the example shown in FIG. 21, the estimation target object is a person 4.

[0109] FIG. 22 shows an example of a distribution diagram of the estimation results of influence, in which a diagram showing the distributions of both the estimation results of the first influence and the estimation results of the second influence is displayed. In the example shown in FIG. 22, the estimation targets are people 4-1 and 4-2, and the second influences corresponding to people 4-1 and 4-2 are displayed as distributions 41-1 and 41-2, respectively. In FIG. 22, the second influence distribution 41-1 corresponding to person 4-1 overlaps with the first influence distribution 32 in region 42. Such a region may be displayed in a display mode corresponding to either the first influence distribution 41-1 or the second influence distribution 41-2. That is, either the distribution 41-1 or the distribution 41-2 may be displayed in region 42. For example, when the first influence distribution and the second influence distribution overlap, which display is to be prioritized may be specified in advance, and the display may be performed based on the specification. Furthermore, although not shown in FIG. 22 , the total influence obtained by adding the first influence and the second influence may be further displayed as a numerical value or the like. For example, the total influence for person 4-1 may be the sum of the value of the first influence at the position of person 4-1 in FIG. 22 and the value of the second influence at the position of moving body 3. That is, for example, the total influence for person 4-1 is the sum of the value at the intersection of first influence distribution 32 and the position of person 4-1 and the value at the intersection of second influence distribution 41-1 for person 4-1 and the position of moving body 3. Furthermore, the total influence for person 4-2 may be the sum of the value of the first influence at the position of person 4-2 in FIG. 22 and the value of the second influence at the position of moving body 3. Furthermore, instead of adding the first influence and the second influence, the first influence and the second influence may be weighted and added. Note that the calculation information of the total influence is not limited to these examples.

[0110] The information processing device 1a of this embodiment is realized, for example, by the computer system illustrated in Fig. 17, similar to the information processing device 1 of the first embodiment. The display information generating unit 18 shown in Fig. 18 is realized by the program stored in the storage unit 103 shown in Fig. 17 being executed by the control unit 101 shown in Fig. 17. The storage unit 103 is also used to realize the display information generating unit 18.

[0111] Note that Figure 18 shows an example in which a display information generation unit 18 is provided instead of the control processing unit 15, but this is not limited to this. The display information generation unit 18 may be added to the information processing device 1 of embodiment 1, and both the operation of embodiment 1 and the operation of this embodiment may be performed.

[0112] As described above, in this embodiment, the estimated impact degree is displayed as a distribution map, so that, for example, an operator controlling the moving object 3 can easily visually grasp the impact degree of the moving object 3. Furthermore, when creating a movement plan, work plan, etc. for the moving object 3, the operator can easily create a plan that takes into account the impact degree of the moving object 3. Furthermore, the distribution map may be displayed superimposed on map information of the facility where the moving object 3 is located. This makes it easier for the operator to determine the movement route of the moving object 3 taking into account the impact degree.

[0113] The configurations shown in the above embodiments are merely examples, and may be combined with other known technologies, or different embodiments may be combined with each other. It is also possible to omit or modify parts of the configurations as long as they do not deviate from the gist of the invention.

[0114] 1, 1a Information processing device, 2 Control target device, 3 Moving object, 4, 4-1, 4-2 Person, 6 Display, 7 Display device, 11 Information storage unit, 12 Estimation unit, 13 First estimation unit, 14 Second estimation unit, 15 Control processing unit, 16 Acquisition unit, 17 Reception unit, 18 Display information generation unit, 51 Imaging device, 52 Gaze direction, 100, 100a Information processing system, 131 Model generation unit, 132 Inference unit.

Claims

1. An information processing device comprising: an estimation unit that estimates an influence level indicating the presence of a moving object when the moving object is operating.

2. The information processing device according to claim 1, further comprising a control processing unit that controls a controlled device, which is at least one of the mobile body and peripheral devices around the mobile body, so that the impact degree approaches a target impact degree.

3. The information processing device described in claim 2, characterized in that the estimation unit estimates the degree of influence that the estimated object, which is at least one of a person and an object, receives from the moving body based on attribute information indicating attributes of the estimated object, and the control processing unit controls a controlled device, which is at least one of the moving body and peripheral equipment around the moving body, based on the estimation result of the estimation unit.

4. The information processing device according to claim 3, wherein the control processing unit further controls the control target device based on surrounding information indicating the situation around the moving object.

5. The information processing device described in claim 4, characterized in that the surrounding information includes at least one of image information obtained by photographing the surroundings of the moving body, biometric information of the person who is the estimated object, and sound information indicating sounds around the moving body.

6. An information processing device as described in any one of claims 3 to 5, characterized in that the control processing unit further controls the controlled device based on at least one of facility information indicating the type of facility in which the mobile body is located and equipment information regarding the equipment in the facility.

7. The information processing device according to any one of claims 3 to 6, wherein the control processing section further uses the attribute information to control the control target device.

8. An information processing device as described in any one of claims 3 to 7, characterized in that the peripheral device includes a display, and the control processing unit causes the display to display an image when it determines, based on the estimation result of the estimation unit, to reduce the degree of influence.

9. An information processing device as described in any one of claims 3 to 8, characterized in that the control processing unit controls the controlled device to increase the degree of impact when it is predicted that an unsafe situation will occur due to contact between the moving body and a person.

10. The information processing device described in claim 9, characterized in that the control processing unit controls the controlled device to increase the degree of influence when it determines that a person is looking away based on image information obtained by photographing the surroundings of the moving body.

11. The information processing apparatus according to claim 8, wherein the image is determined based on the attribute information.

12. An information processing device described in any one of claims 3 to 11, characterized in that the influence level includes a first influence level indicating the degree of influence the moving body has on the surroundings when operating, and a second influence level indicating the degree of influence the object to be estimated receives from the moving body, the estimation unit comprises: a first estimation unit that estimates the first influence level; and a second estimation unit that estimates the second influence level, and the control processing unit controls the controlled device based on the first influence level and the second influence level.

13. An information processing device according to any one of claims 1 to 12, characterized in that it comprises a display information generation unit that generates display information showing the estimation results of the estimation unit as a distribution map and outputs the display information to a display device.

14. The information processing device described in claim 13, characterized in that the influence level includes a first influence level indicating the degree of influence the moving body has on its surroundings when operating, and a second influence level indicating the degree of influence the moving body has on an estimated object, which is at least one of a person and an object, and the estimation unit comprises: a first estimation unit that estimates the first influence level; and a second estimation unit that estimates the second influence level, and the display information generation unit generates the display information based on the first influence level and the second influence level.

15. An information processing device as described in claim 12 or 14, characterized in that the first estimation unit estimates the first influence degree based on at least one of the direction of movement of the mobile body and equipment information regarding equipment in the facility where the mobile body is located.

16. An information processing device as described in any one of claims 12, 14 and 15, characterized in that the first estimation unit estimates the first influence level based on at least one of the color, size and operation mode of the moving object.

17. The information processing device according to claim 15, wherein the facility information includes information indicating at least one of the position and shape of walls and the position and shape of roads in the facility.

18. An information processing device according to any one of claims 12, 14, 15, 16 and 17, characterized in that the second estimation unit estimates the second influence level based on attribute information indicating attributes of the estimation target object.

19. An information processing method in an information processing device, comprising: an estimation step of estimating an influence level indicating the presence of a moving object when the moving object is operating.

20. A program causing a computer system to execute an estimation step of estimating the degree of influence indicating the presence of a moving object when the moving object is operating.

Images