Robot control device, method and program

Through the attribute determination unit and the determination unit of the robot control device, the notification action is decided based on the attributes and hazard risks of the target person, and the problem of excessive or insufficient notification content in the prior art is solved, and appropriate notification effect is achieved.

CN114206561BInactive Publication Date: 2024-12-03SONY GROUP CORP
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202080056064.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Priority Date
2019-08-14
Filing Date
2020-06-24
Publication Date
2024-12-03
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

In the prior art, the robot may have too much or insufficient notifications to the target person due to perceived differences, and it is impossible to properly provide personalized notifications based on the target person's attributes and hazard risks.

Method used

A robot control device is designed to identify the attributes and hazard risks of the object human through attribute determination unit, and the decision unit determines the notification action according to the intervention level, including a direct or indirect notification method to appropriately notify the object human of the existence of the robot.

Benefits of technology

Personalized notifications are achieved based on the attributes and hazard risks of the object person, ensuring the appropriateness of the notification content, avoiding excessive or insufficient notification problems, and improving the object person's attention to the existence of the robot.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114206561B_ABST
    Figure CN114206561B_ABST
Patent Text Reader

Abstract

A robot control device (10) comprises: an attribute determination unit (71) which determines the attributes of a target (T) in an area around a robot (1); and a decision unit (74) which decides whether to take a notification action based on the attributes determined by the attribute determination unit (71) and the risk of harm associated with the risk of harm that the robot (1) may present to the target (T), wherein a notification of the presence of the robot (1) is given from the robot (1) to the target (T).
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to a robot control device, method, and program. Background Art

[0002] There is a technology that notifies a surrounding target person of a potential harm that may be caused by the robot to the surrounding target person through the robot's display. In order to avoid harm, such a robot corrects the operation mode according to the correction amount and changes the display mode of the robot's display.

[0003] Reference List

[0004] Patent Literature

[0005] Patent Document 1: JP 2007-196298 A Summary of the invention

[0006] Technical issues

[0007] However, in the prior art, there is room for improvement in the appropriate notification from the robot to the target person. For example, due to different perceptions between target persons, the same notification content may be too much notification content for one target person, or insufficient notification content for another target person.

[0008] The present application has been made in view of the above, and an object of the present application is to provide a robot control apparatus, method, and program configured to provide appropriate notification.

[0009] Solution to the problem

[0010] A robot control device includes: an attribute determination unit, which determines the attributes of a target person around the robot; and a decision unit, which determines a notification action of notifying the target person of the robot's existence through the robot based on the attributes determined by the attribute determination unit and the risk of harm that the robot may cause to the target person.

[0011] According to one aspect of the embodiment, appropriate notification may be provided.It should be noted that the effects described here are not necessarily restrictive, and any effects described in the present disclosure may be provided. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 : is a diagram showing an overview of a robot control device according to an embodiment.

[0013] Figure 2 is a block diagram showing a configuration example of a robot control device according to an embodiment.

[0014] Figure 3 is a table showing an example of target person information according to an embodiment.

[0015] Figure 4 is a diagram showing an example of a body characteristic table according to an embodiment.

[0016] Figure 5 is a diagram showing an example of an ease level table according to an embodiment.

[0017] Figure 6 is a diagram showing an example of an understanding level table according to an embodiment.

[0018] Figure 7 is a diagram showing an example of a risk table according to an embodiment.

[0019] Figure 8 is a diagram illustrating an example of intervention levels according to an embodiment.

[0020] Fig. 9 is a flowchart showing a processing procedure executed by a robot control device according to an embodiment.

[0021] Fig.10 is a hardware configuration diagram showing an example of a computer that realizes the function of the robot control device. DETAILED DESCRIPTION

[0022] Embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. Note that in the following embodiments, the same parts are represented by the same reference numerals or symbols, and repeated descriptions thereof will be omitted.

[0023] Implementation

[0024] [Configuration of System According to Embodiment]

[0025] First, an overview of the embodiments of the present disclosure will be described. As described above, there is a technology for notifying a surrounding target person of potential harm that may be caused by a robot to the surrounding target person through a display of a robot. However, in such a technology, there is room for improvement in optimizing the content of the notification to the target person. For example, even if the same notification content is provided, the target person may perceive the content differently.

[0026] Specifically, for example, although the target person who contacts the robot every day is familiar with the robot's action mode, the target person who contacts the robot for the first time is not familiar with the robot's action mode. For this reason, for example, when the same notification content is provided to two target persons, the same notification content may be excessive notification content or may be insufficient notification content.

[0027] In view of the above viewpoints, the technical concept of the present invention has been conceived, and the notification content can be set for each target person to provide appropriate notification. In addition, in the present technical concept, notification is provided considering the risk of harm that the robot may cause to the target person (hereinafter referred to as the risk of harm).

[0028] First, refer to Figure 1 An overview of the robot control device according to the present embodiment is described. Figure 1 1 is a diagram showing an overview of a robot control device according to the present embodiment. Figure 1 As shown, the robot control device 10 is a control device built in the robot 1 to control the robot 1 .

[0029] For example, robot 1 is a mobile robot and Figure 1 In the example shown, the robot 1 is a wheeled robot. Here, the robot may be a legged robot or a flying mobile body. In addition, the robot may include at least one or more arms, or may be an armless mobile body.

[0030] For example, the robot control device 10 detects the target person T around the robot 1 based on the sensing results from the sensor S that senses the periphery of the robot 1, and determines the notification action of the robot 1 to the target person T based on the attributes of the target person T and the risk of harm that the robot 1 may cause to the target person T.

[0031] Notice, Figure 1 The illustrated example shows the sensor S provided separately from the robot 1 , but the sensor S may be provided inside the robot 1 , or a wearable device worn by the target person T may be used as the sensor S.

[0032] For example, the robot control device 10 determines whether the target person T is a user who normally contacts the robot 1 as an attribute of the target person T, and determines the risk of harm based on the current state of the robot 1, the distance between the target person T and the robot 1, and the like.

[0033] Then, the robot control device 10 calculates an intervention level at which the robot 1 should intervene with respect to the target person T based on the above-mentioned attributes and the risk of harm. Here, the intervention level indicates the degree to which the target person T should be notified of the presence of the robot 1 .

[0034] The robot controller 10 determines a notification operation that is easy for the target person T to notice when the intervention level is higher, and determines a minimum notification operation when the intervention level is lower.

[0035] As described above, the robot controller 10 according to the embodiment decides the notification action according to the intervention level, and therefore, the notification action can be appropriately decided according to the attribute of the target person T and the risk of harm.

[0036] [Configuration of robot control device according to embodiment]

[0037] Next, we will refer to Figure 2 A configuration example of the robot control device 10 according to the embodiment is described. Figure 2 : is a block diagram showing a configuration example of the robot control device 10 according to the embodiment.

[0038] like Figure 2 As shown, the robot control device 10 includes a remote operation receiving unit 2, an input unit 3, an output unit 4, a drive unit 5, a storage unit 6, and a control unit 7. The remote operation receiving unit 2 is a communication unit that receives a remote operation of the robot 1.

[0039] The input unit 3 inputs the sensing result of the environment sensing around the robot 1 to the control unit 7. Figure 2 In the example shown, the input unit 3 includes a laser distance measuring device 31 , an RGB camera 32 , a stereo camera 33 , and an inertial measurement unit 34 .

[0040] The laser distance measuring device 31 is a device that measures the distance to an obstacle, and includes an infrared distance measuring device, an ultrasonic distance measuring device, a laser imaging detection and ranging (LiDAR), and the like.

[0041] The RGB camera 32 is an imaging device that captures an image (still image or moving image). The stereo camera 33 is an imaging device that images a subject from multiple directions to measure the distance to the subject person. For example, the inertial measurement unit 34 is a device that detects acceleration and angles of three axes.

[0042] The output unit 4 is provided in the robot 1 and includes a display device or a speaker, for example. The output unit 4 outputs an image or a sound input from the control unit 7. The drive unit 5 includes an actuator and drives the robot 1 based on control of the control unit 7.

[0043] The storage unit 6 stores target person information 61 , model information 62 , a physical characteristic table 63 , an ease level table 64 , an understanding level table 65 , a risk table 66 , an intervention level table 67 , and an action table 68 .

[0044] The target person information 61 is information about the target person T. In the embodiment, the target person information 61 is information about the number of times and the frequency of contact of the target person T with the robot 1 . Figure 3 : is a table showing an example of the target person information 61 according to the embodiment.

[0045] like Figure 3As shown, the target person information 61 is information in which "target person ID", "feature amount", "contact history", "recognition level" and the like are associated with each other. "Target person ID" is an identifier for identifying the target person T. "Feature amount" indicates a feature amount corresponding to the target person T. For example, the feature amount is information on the feature amount of the face of the target person T.

[0046] The “contact history” is information about the contact history between the corresponding target person T and the robot 1. In other words, the contact history here is the history of the robot 1 recognizing the target person T. For example, in the contact history, information about the date and time, frequency, etc., at which the robot 1 recognizes the target person T is recorded.

[0047] The “recognition level” indicates the degree of recognition of the robot 1 by the corresponding target person T. In the present embodiment, the recognition level is set according to the number of times or frequency of contact with the robot 1 based on the contact history.

[0048] In the present embodiment, the recognition level is expressed as three levels, and "A" indicates the highest recognition level, and "C" indicates the lowest recognition level. For example, the recognition level "A" indicates continuous contact with the robot 1, and the object person T indicated by the recognition level "C" is in contact with the robot for the first time. In other words, the recognition level is set higher according to the number of times the object person T is in contact with the robot 1.

[0049] Back to Figure 2 , the model information 62 will be described. The model information 62 is information about a model for determining the physical characteristics of the target person T based on the image data. For example, the model includes a model for estimating the age of the target person T and a model for determining whether the target person T walks with a cane or uses a wheelchair.

[0050] The physical characteristic table 63 is a table of physical characteristics of the target person T. Figure 4 63 is a diagram showing an example of the physical characteristic table 63 according to an embodiment. Figure 4 As shown, the physical characteristic table 63 is a table showing the level of each of the items of “age” and “others” as physical characteristics.

[0051] The physical characteristics are each arranged into three levels of A, B, and C, and each physical characteristic decreases in the order of A, B, and C. Figure 4 In the example of , people under 8 years old are represented by "C", people between 8 and 15 years old or over 50 years old are represented by "B", and people between 15 and 50 years old are represented by "A".

[0052] In the case where the subject T is younger than 8 years old or older than 50 years old, it is assumed that the subject T has difficulty seeing farther and has difficulty understanding the operation of the robot 1. Therefore, the level of physical characteristics of the subject T younger than 8 years old or older than 50 years old is lower than that of the subject T aged 8 to 15 years old.

[0053] In addition, Figure 4 In "Others" of , the level of physical characteristics of the subject T who walks with a cane or the subject T who uses a wheelchair or a walker is lower than the level of physical characteristics of a healthy person. Note that Figure 4 The illustrated physical property table 63 is an example and is not limited thereto.

[0054] Back to Figure 2 , the ease level table 64 will be described. The ease level table 64 is a table showing the ease level of recognition of the hazardous factor of the robot 1 to the target person T by the target person T. Figure 5 is a diagram showing an example of the ease level table 64 according to the embodiment.

[0055] like Figure 5 As shown, the ease level table 64 is a table showing the relationship between the recognizability level and the five senses. Here, the five senses indicate which organ of the target person T is used to recognize the hazard factor of the robot 1.

[0056] For example, the recognizable level of the hazard factor of the robot 1 is represented by "A" only by touch or taste, and the recognizable level of the hazard factor is represented by "B" only by vision or smell. In addition, the recognizable level of the hazard factor is represented by "C" by hearing.

[0057] For example, in the case where the hazard factor is the heating of the robot 1, the subject person T can recognize the hazard factor only by the sense of touch, and the recognizability level is represented by "A". In addition, in the case where the subject person T can recognize the hazard factor by sight or smell, the recognition becomes easy, and the recognizability level is represented by "B". Furthermore, in the case where the hazard factor can be recognized by hearing, since the hazard factor can be recognized from a farther distance, and therefore, the ease of recognition is set to "C".

[0058] Back to Figure 2 , the understanding level table 65 will be described. The understanding level table 65 is a table of the understanding level of the target person T with respect to the robot. Figure 6 is a diagram showing an example of the understanding level table 65 according to the embodiment.

[0059] like Figure 6 As shown, the understanding level table 65 is a table for calculating the understanding level based on the physical characteristics and the cognizable level. Figure 4In the example of , when the ease of recognition and the recognition level are both "A", the understanding level is "A". In addition, when the ease of recognition is "A" and the physical characteristics are "B", according to Figure 3 The level of recognition shown determines the level of comprehension.

[0060] Specifically, when the recognition level is C or B, the comprehension level is "B", and when the recognition level is "A", the comprehension level is "A". Figure 6 In the example shown, the level of understanding decreases as the level of ease of recognition decreases, and the level of understanding decreases as the level of physical characteristics decreases.

[0061] Back to Figure 2 , the risk table 66 will be described. The risk table 66 is a table of risks of harm that the robot 1 may cause to the target person T. Figure 7 is a diagram showing an example of the risk table 66 according to the embodiment. Figure 7 As shown, the risk table 66 is a table for determining the risk of a hazard based on the impact level and the contact time / distance.

[0062] Here, the impact level indicates the magnitude of harm to the target person T when the robot 1 causes harm to the target person T. For example, the impact level indicated when the target person T is seriously injured is "A", the impact level indicated when the target person T is slightly injured is "B", and the impact level indicated when the target person T is not injured is "C".

[0063] Here, in the case where the impact level can be reduced in advance, the already reduced impact level is applied. For example, in the case where the robot 1 is a double bowl robot and one arm is damaged and sharpened, the impact level can be reduced if the damaged arm is retracted and switched to another undamaged arm.

[0064] in addition, Figure 7 The “contact time / distance” shown indicates the time / distance until the robot 1 comes into contact with the target person T. The contact time / distance is calculated based on the distance between the robot 1 and the target person T or the speed at which both the robot 1 and the target person T move.

[0065] For example, when the distance between the robot 1 and the target person T is 3 m or less or the contact time is 3 seconds or less, the contact time / distance is "C", and when the distance between the robot 1 and the target person T is 5 m or less or the contact time is 5 seconds or less, the contact time / distance is "B". When the distance between the robot 1 and the target person T is 5 m or more or the contact time is 5 seconds or more, the contact time / distance is "A".

[0066] Then, in Figure 7In the example shown, the higher the impact level, the higher the risk of harm, and the smaller the contact time / distance, the higher the risk of harm.

[0067] Back to Figure 2 , the intervention level table 67 will be described. The intervention level table 67 is a table for calculating the intervention level based on the risk and understanding level of the hazard. Figure 8 is a diagram showing an example of the intervention level table 67 according to the embodiment.

[0068] like Figure 8 As shown, the intervention level table 67 is a table showing the relationship between the risk of harm, the level of understanding and the intervention level. Figure 8 In the example shown, the higher the level of understanding, the lower the level of intervention, and the higher the risk of harm, the higher the level of intervention.

[0069] Back to Figure 2 , the action table 68 will be described. The action table 68 is a table that defines notification actions according to intervention levels. In addition, in the present embodiment, notification actions according to hazard factors are defined in the action table 68.

[0070] The control unit 7 has a function of controlling each configuration of the robot control device 10. Figure 2 As shown, the control unit 7 includes an attribute determination unit 71 , a state determination unit 72 , a calculation unit 73 , a decision unit 74 and a behavior detection unit 75 .

[0071] The attribute determination unit 71 determines the attribute of the target person T. Specifically, for example, the attribute determination unit 71 extracts the feature quantity of the target person T from the image data captured by the RGB camera 32, and compares the feature quantity of the target person T with the feature quantity of the target person information 61 to determine whether the target person T is a person registered in the target person information 61.

[0072] Then, when the target person T is registered in the target person information 61 , the attribute determination unit 71 extracts the recognition level of the target person T, and when the target person T is not registered in the target person information 61 , the attribute determination unit 71 newly registers the target person in the target person information 61 .

[0073] Furthermore, when the robot 1 moves along the planned travel route, the attribute determination unit 71 selects an object person T that may collide with the robot 1, and determines the physical characteristics of the object person T based on the image data of the object person T. Specifically, as described above, the attribute determination unit 71 determines the age of the object person T and the presence or absence of a cane, a wheelchair, a walker, etc. based on the model information 62.

[0074] Then, the attribute determination unit 71 decides the level of the physical property of the target person T based on the physical property table 63. In addition, the attribute determination unit 71 refers to the understanding level table 65 based on the cognizability level notified by the state determination unit 72 (described later), and decides the level of the understanding level of the target person T with respect to the robot 1. In other words, the attribute determination unit 71 decides the understanding level depending on whether the hazardous factor of the robot 1 is recognized by which organ.

[0075] The state determination unit 72 determines the state of the robot 1. Specifically, for example, the state determination unit 72 determines the state of the robot 1 by using image data obtained by imaging the robot 1, a temperature sensor provided in the robot 1, and the like.

[0076] For example, the state determination unit 72 determines the presence or absence of a malfunction of the robot 1 , the presence or absence of a conveyance, the contents of the conveyance, etc. based on image data, and determines the surface temperature of the robot 1 by using a temperature sensor, etc.

[0077] Then, the state determination unit 72 determines the current “influence level” of the robot 1 according to the determined state (see Figure 7 ). In addition, information on the content of the transported object determined by the state determination unit 72 is notified to the determination unit 74.

[0078] The calculation unit 73 calculates an intervention level at which the robot 1 should intervene with respect to the target person T based on the attribute of the target person T determined by the attribute determination unit 71 and the mental risk that the robot 1 may cause to the target person T.

[0079] Specifically, for example, when the robot 1 moves along the current planned travel route, the calculation unit 73 selects a target person T that may come into contact with the robot 1 . Next, the calculation unit 73 calculates the distance to the target person T based on the measurement results of the laser distance measuring device 31 and the stereo camera 33 .

[0080] Furthermore, the calculation unit 73 is configured to track the target person T to calculate the moving speed and moving direction of the target person T, and calculate the current speed and direction of the robot 1 based on the detection result of the inertial measurement unit 34 .

[0081] Then, the calculation unit 73 calculates the above-mentioned contact time / distance based on the distance and speed, and determines the level of the contact time / distance. Thereafter, the calculation unit 73 refers to the risk table 66 based on the "contact time / distance" and "impact level" determined by the state determination unit 72, and calculates the risk of harm.

[0082] Here, as described above, the smaller the contact time / distance, the higher the risk of harm. In other words, when the distance between the robot 1 and the target person T decreases, the risk of harm increases. Therefore, the calculation unit 73 calculates the contact time / distance as needed and updates the risk of harm. Therefore, appropriate notification can be provided according to the risk of harm.

[0083] The decision unit 74 decides a notification action of the robot 1 to notify the target person T of the presence of the robot 1 based on the attribute determined by the attribute determination unit 71 and the risk of harm that the robot 1 may cause to the target person T.

[0084] Specifically, the decision unit 74 decides the notification action based on the intervention level calculated by the calculation unit 73. In the present embodiment, the decision unit 74 selects a notification method for the notification action according to the intervention level. Here, as described below, the notification method includes a direct notification method and an indirect notification method.

[0085] For example, in a case where the intervention level is “A”, the decision unit 74 selects the direct notification method and decides a notification action that makes the target person T reliably notice the presence of the robot 1 .

[0086] Specifically, a warning image is displayed on the output unit 4, or a warning sound is output from the output unit 4 to attract the presence of the robot 1 directly to the target person T. Note that in this configuration, for example, a light emitter such as a lamp may be blinked to attract the presence of the robot 1 to the target person T.

[0087] Furthermore, in the case where the target person T is about to touch the robot 1 having a damaged or heated arm, the decision unit 74 may perform an action of prompting the target person T to hold a part other than the arm (eg, a torso).

[0088] Furthermore, when the intervention level is "B", that is, when the intervention level is within a predetermined range, the decision unit 74 decides a notification action for indirectly notifying the hazardous factor of the robot 1. For example, the decision unit 74 decides an action that indicates the content of the transported object transported by the robot 1 as the notification action.

[0089] When the robot 1 is carrying a heavy object, it is considered that the robot 1 may come into contact with the target person T and drop the object on the target person T. Therefore, the decision unit 74 decides an action suggesting that the robot 1 is carrying a heavy object as the notification action.

[0090] Specifically, the decision unit 74 decides as the notification action an action indicating that the robot 1 is shaking due to the weight of the object being transported. In addition, when the robot 1 is transporting a container containing a liquid, the decision unit 74 decides as the notification action an action in which an arm different from the arm holding the container is placed on the container. Therefore, it can be suggested that the object being transported is a liquid.

[0091] Furthermore, in the case where the arm is damaged and there is a risk that the target person T may be injured when the arm touches the target person T, the action of swinging the arm according to the shaking when the robot 1 moves is determined as the notification action. Therefore, the damage of the arm can be indirectly notified to the target person. When the intervention level is "C", the notification action is not performed.

[0092] The decision unit 74 causes the output unit 4 to display a warning image thereon, or causes the drive unit 5 to drive according to the decided notification action, and thus, can cause the robot 1 to perform the notification action.

[0093] Then, the decision unit 74 decides the next notification action after the notification action based on the behavior of the target person T detected by the behavior detection unit 75 described later. Specifically, when the target person T takes a behavior indicating understanding of the notification action, the decision unit 74 stops the notification action and returns to the execution of the original task.

[0094] Note that in this configuration, the decision unit 74 may perform the original task while continuing the notification action at a fixed intervention level.

[0095] Meanwhile, when the target person T does not understand the notification action, the decision unit 74 continues to perform the notification action according to the current intervention level. Here, as described above, the intervention level is updated according to the distance between the robot 1 and the target person T. Therefore, as the distance between the robot 1 and the target person T decreases, the intervention level increases, thereby performing the notification action according to the change in the intervention level.

[0096] Furthermore, as described above, in the case where the arm is damaged or heated, when the level of influence can be reduced by alternative means, the decision unit 74 allows an action such as retracting the damaged arm.

[0097] The behavior detection unit 75 detects the behavior of the target person T. The behavior detection unit 75 analyzes the image data captured by the RGB camera 32 to detect the behavior of the target person T.

[0098] In the present embodiment, the behavior detection unit 75 detects a behavior related to whether the target person T understands the notification action of the robot 1 as the behavior of the target person T. Specifically, for example, the behavior detection unit 75 detects behaviors such as whether the target person T checks the notification action of the robot 1 or whether the moving speed of the target person T changes before and after the notification action.

[0099] In other words, the robot controller 10 pays attention to the point that the target person T behaves differently when he understands the notification action and when he does not understand the notification action, and decides the next action after the notification action.

[0100] Therefore, there is no need to perform excessive notification actions, and therefore, the target person T can be appropriately notified of the presence of the robot 1 .

[0101] Next, we will refer to Fig. 9 A processing procedure executed by the robot controller 10 according to the present embodiment will be described. Fig. 9 : is a flowchart showing a processing procedure executed by the robot controller 10 .

[0102] like Fig. 9 As shown, the robot control device 10 first determines the state of the robot 1 (step S101), and calculates the influence level based on the hazard factor (step S102). Subsequently, the robot control device 10 determines whether the influence level calculated in step S102 is higher than "C" (step S103), and when the influence level is higher than "C" (step S103, yes), the robot control device 10 determines whether there is an object person T that may come into contact with the robot 1 (step S104).

[0103] When the target person T is found in the determination of step S104 (step S104 , Yes), the robot controller 10 determines the attribute of the target person T (step S105 ) and calculates the intervention level (step S106 ).

[0104] Then, the robot controller 10 determines a notification operation based on the intervention level (step S107 ), and causes the robot 1 to execute the determined notification operation (step S108 ).

[0105] Subsequently, the robot control device 10 determines whether the behavior of the target person T of the recognition robot 1 is detected (step S109), and when such behavior is detected (step S110), the original task is executed (step S110), and the process ends.

[0106] On the other hand, when the behavior is not detected in the determination of step S109 (step S109 , No), the robot controller 10 updates the contact time / distance (step S111 ), and proceeds to step S106 .

[0107] Furthermore, when the influence level is “C” in the determination of step S103 (step S103 , No), or when the target person does not exist in the determination process of step S104 (step S104 , No), the robot controller 10 proceeds to step S110 .

[0108] In addition, in each process described in the above embodiments, all or part of the process described as being automatically performed may also be performed manually, or all or part of the process described as being manually performed may also be automatically performed by a known method. In addition, unless otherwise specified, the processing procedures, specific names, and information including various data and parameters shown in the above description or drawings may be appropriately changed. For example, the various information shown in the drawings is not limited to the information shown.

[0109] In addition, the constituent elements of the device are shown as functional concepts and do not necessarily have to be physically configured as shown. In other words, the specific forms of distribution or integration of the device are not limited to those shown, and all or part of it can be configured to be functionally or physically distributed or integrated in arbitrary units according to various loads or usage conditions.

[0110] Furthermore, the above-described embodiments and modifications may be appropriately combined within a range consistent with the processing contents.

[0111] Furthermore, the effects described herein are merely examples, and the present disclosure is not limited to these effects and may have other effects.

[0112] For example, an information device such as the robot control device, HMD, and controller according to the above-mentioned embodiment is composed of Fig.10 The computer 1000 shown is implemented. Hereinafter, the robot control device 10 according to the embodiment will be described as an example. Fig.10 10 is a hardware configuration diagram showing an example of a computer 1000 that realizes the functions of the robot control device 10. The computer 1000 includes a CPU 1100, a RAM 1200, a read-only memory (ROM) 1300, a hard disk drive (HDD) 1400, a communication interface 1500, and an input / output interface 1600. The constituent units of the computer 1000 are connected by a bus 1050.

[0113] The CPU 1100 operates based on the program stored in the ROM 1300 or the HDD 1400 and controls each unit. For example, the CPU 1100 schedules and deploys the program stored in the ROM 1300 or the HDD 1400 to the RAM 1200 and executes processing corresponding to various programs.

[0114] The ROM 1300 stores a boot program such as a basic input output system (BIOS) executed by the CPU 1100 when the computer 1000 is started, a program depending on the hardware of the computer 1000 , and the like.

[0115] The HDD 1400 is a computer-readable recording medium that non-transitorily records a program executed by the CPU 1100 , data used by the program, and the like. Specifically, the HDD 1400 is a recording medium that records a program according to the present disclosure as an example of program data 1450 .

[0116] The communication interface 1500 is an interface that connects the computer 1000 to an external network 1550 (eg, the Internet). For example, the CPU 1100 receives data from another device via the communication interface 1500 or transmits data generated by the CPU 1100 to another device.

[0117] The input / output interface 1600 is an interface for connecting the input / output device 1650 to the computer 1000. For example, the CPU 1100 receives data from an input device such as a keyboard or a mouse via the input / output interface 1600. In addition, the CPU 1100 sends data to an output device such as a display, a speaker, or a printer via the input / output interface 1600. In addition, the input / output interface 1600 can be used as a medium interface for reading a program recorded on a predetermined recording medium, etc. For example, the medium includes an optical recording medium such as a digital versatile disk (DVD) and a phase change rewritable disk (PD), a magneto-optical recording medium such as a magneto-optical disk (MO), a magnetic tape medium, a magnetic recording medium, a semiconductor memory, etc.

[0118] For example, when the computer 1000 is used as the robot control device 10 according to the embodiment, the CPU 1100 of the computer 1000 implements the functions of the attribute determination unit 71 and the like by executing the program loaded on the RAM 1200. In addition, the HDD 1400 stores the program according to the present disclosure and the data stored in the storage unit 6. Note that the CPU 1100 executes the program data 1450 read from the HDD 1400, but in another example, the CPU 1100 may acquire the program from other devices via the external network 1550.

[0119] Note that the present technology can also adopt the following configurations.

[0120] (1) A robot control device comprising:

[0121] an attribute determination unit that determines an attribute of a target person around the robot; and

[0122] A decision unit that decides a notification action of notifying the target person of the presence of the robot by the robot based on the attribute determined by the attribute determination unit and a risk of harm as a risk of harm caused by the robot to the target person.

[0123] (2) The robot control device according to (1), further comprising

[0124] a calculation unit that calculates an intervention level at which the robot should intervene in the target person based on the attribute and the hazard risk,

[0125] The decision unit determines the notification action based on the intervention level calculated by the calculation unit.

[0126] (3) The robot control device according to (2), wherein:

[0127] The decision unit changes a notification method of the notification action based on the intervention level.

[0128] (4) The robot control device according to any one of (1) to (3), wherein:

[0129] The attribute determination unit determines the attribute based on a level of understanding of the robot by the target person.

[0130] (5) The robot control device according to any one of (1) to (3), wherein:

[0131] The attribute determination unit determines the attribute based on a physical feature of the target person.

[0132] (6) The robot control device according to any one of (2) to (5), wherein:

[0133] The calculation unit calculates the intervention level to be higher as the risk of harm is higher.

[0134] (7) The robot control device according to any one of (2) to (6), wherein:

[0135] The calculation unit calculates the risk of the hazard based on the distance between the robot and the target person.

[0136] (8) The robot control device according to any one of (2) to (7), wherein:

[0137] The calculation unit calculates the risk of the hazard based on the speed at which the target person approaches the robot.

[0138] (9) The robot control device according to any one of (2) to (8), further comprising

[0139] a state determination unit that determines a hazard factor that is a potential hazard to the target person based on the state of the robot,

[0140] The calculation unit calculates the risk of the hazard based on the hazard factor determined by the state determination unit.

[0141] (10) The robot control device according to (9), wherein:

[0142] The state determination unit determines the hazardous factor based on a surface temperature of the robot.

[0143] (11) The robot control device according to (9) or (10), wherein:

[0144] The state determination unit determines the hazardous factor based on the presence or absence of the robot

[0145] (12) The robot control device according to any one of (9) to (11), wherein:

[0146] The state determination unit determines the hazardous factor based on an object being transported by the robot.

[0147] (13) The robot control device according to (12), wherein:

[0148] The determination unit determines an action suggesting the conveyed object as the notification action.

[0149] (14) The robot control device according to any one of (9) to (13), wherein:

[0150] The determination unit determines the notification action based on a level of cognition of the hazard factor by the target person.

[0151] (15) The robot control device according to any one of (9) to (14), wherein:

[0152] The decision unit determines whether to perform a next notification action based on the behavior of the target person after the notification action.

[0153] (16) The robot control device according to (15), wherein:

[0154] When the intervention level is within a predetermined range, the decision unit decides an operation action suggesting the hazardous factor as the notification action.

[0155] (17) The robot control device according to any one of (1) to (16), wherein:

[0156] When the intervention level exceeds the predetermined range, the decision unit decides to output at least one of an image and a sound as the notification action.

[0157] (18) A method implemented by a computer, comprising:

[0158] Determining attributes of a target person around the robot; and

[0159] Based on the determined attribute and the harm risk which is the risk regarding harm caused by the robot to the target person, a notification action of notifying the target person of the presence of the robot by the robot is decided.

[0160] (19) A program causing a computer to function as follows:

[0161] an attribute determination unit that determines an attribute of a target person around the robot; and

[0162] A decision unit that decides a notification action of notifying the target person of the presence of the robot by the robot based on the attribute determined by the attribute determination unit and a risk of harm as a risk of harm caused by the robot to the target person.

[0163] Reference Mark List

[0164] 1. Robot

[0165] 10 Robot control device

[0166] 71 Attribute determination unit

[0167] 72 Status determination unit

[0168] 73 Computational Units

[0169] 74 Decision Unit

[0170] 75 Behavior Detection Unit

Claims

1. A robot control device, comprising: an attribute determination unit that determines an attribute of a target person around the robot; a decision unit that decides a notification action of notifying the target person of the existence of the robot by the robot, based on the attribute determined by the attribute determination unit and a risk of harm as a risk regarding harm caused by the robot to the target person; as well as a state determination unit that determines a hazard factor that is a potential hazard to the target person based on the state of the robot, wherein the attribute determination unit determines the attribute based on the target person's level of understanding of the robot, and The determination unit determines the notification action based on a level of cognition of the hazard factor by the target person associated with the five senses.

2. The robot control device according to claim 1, further comprising: a calculation unit that calculates an intervention level at which the robot should intervene in the target person based on the attribute and the hazard risk, The decision unit further determines the notification action based on the intervention level calculated by the calculation unit.

3. The robot control device according to claim 2, wherein: The decision unit changes a notification method of the notification action based on the intervention level.

4. The robot control device according to claim 1, wherein: The attribute determination unit determines the attribute based on a physical feature of the target person.

5. The robot control device according to claim 2, wherein: The calculation unit calculates the intervention level to be higher as the risk of harm is higher.

6. The robot control device according to claim 2, wherein: The calculation unit calculates the hazard risk based on a distance between the robot and the target person.

7. The robot control device according to claim 2, wherein: The calculation unit calculates the hazard risk based on a speed at which the target person approaches the robot.

8. The robot control device according to claim 2, wherein: The calculation unit calculates the hazard risk based on the hazard factor determined by the state determination unit.

9. The robot control device according to claim 8, wherein: The state determination unit determines the hazardous factor based on a surface temperature of the robot.

10. The robot control device according to claim 8, wherein: The state determination unit determines the hazardous factor based on the presence or absence of the robot.

11. The robot control device according to claim 8, wherein: The state determination unit determines the hazardous factor based on an object being transported by the robot.

12. The robot control device according to claim 11, wherein: The determination unit determines an action suggesting the conveyed object as the notification action.

13. The robot control device according to claim 1, wherein: The decision unit determines whether to perform a next notification action based on the behavior of the target person after the notification action.

14. The robot control device according to claim 8, wherein: When the intervention level is within a predetermined range, the decision unit decides an operation action suggesting the hazardous factor as the notification action.

15. The robot control device according to claim 14, wherein: When the intervention level exceeds the predetermined range, the decision unit decides to output at least one of an image and a sound as the notification action.

16. A method implemented by a computer, comprising: Determine the attributes of the target person around the robot; determining, based on the determined attribute and the harm risk as a risk regarding harm caused by the robot to the target person, a notification action of notifying the target person of the presence of the robot by the robot; as well as determining a hazard factor that is a potential hazard to the target person based on the state of the robot, wherein the attribute is determined based on the target person's level of understanding of the robot, and The notification action is determined based on a level of cognition associated with the five senses of the target person in recognizing the hazardous factor.

17. A computer-readable storage medium having stored thereon a program, the program causing a computer to function as: an attribute determination unit that determines an attribute of a target person around the robot; a decision unit that decides a notification action of notifying the target person of the existence of the robot by the robot, based on the attribute determined by the attribute determination unit and a risk of harm as a risk regarding harm caused by the robot to the target person; as well as a state determination unit that determines a hazard factor that is a potential hazard to the target person based on the state of the robot, wherein the attribute determination unit determines the attribute based on the target person's level of understanding of the robot, and The determination unit determines the notification action based on a level of cognition of the hazard factor by the target person associated with the five senses.