WO2024203621A1 - Information processing method, information processing device, and program - Google Patents

Abstract

The invention of the present disclosure acquires an operation parameter to be applied to a robot when there is an environmental change, proposes the acquired operation parameter to a user, and applies the proposed operation parameter to the robot when the proposal for the proposed operation parameter is accepted.

Description

Information processing method, information processing device, and program

This disclosure relates to an information processing method, an information processing device, and a program.

There is a control device for a robot that is equipped with an environmental information acquisition unit such as a video camera or microphone, a current position detection unit, and a map management unit, and moves autonomously while referring to environmental information within the movement area.

The robot control device has a storage means for control parameters adapted to the environment in order to optimally control the robot in response to different environments, and identifies the current position on the map based on a signal from the current position detection means, searches for control parameters adapted to that area, and controls the robot's movement functions or environmental information acquisition unit using the searched control parameters.

JP 2006-75948 A

However, the robot's operating parameters may no longer be optimal over time. For example, a robot may move slowly when first introduced, but as the user becomes accustomed to it, it may feel slow, or the child may grow older and the avoidance range may be reduced, or an unfamiliar person may approach and the robot may want to move at a slower speed.

In addition, there was a problem in that even if new control parameters were to be set, there was no basis for doing so, making it impossible to set accurate control parameters for the robot.

The present disclosure has been made in consideration of the above problems, and relates to an information processing method, information processing device, and program that can set robot control parameters with high accuracy even if they change over time.

The information processing method disclosed herein acquires operation parameters to be changed and applied to the robot when an environmental change occurs, proposes the acquired operation parameters to a user, and applies the proposed operation parameters to the robot when the proposed operation parameters are accepted.

1 is a functional block diagram of an information processing system according to an embodiment. FIG. 4 is a diagram showing an example of operation parameters of a robot according to an embodiment. FIG. 4 is a diagram showing an example of environmental information of a robot according to an embodiment; FIG. 11 is a diagram for explaining patterning in a server according to an embodiment. 11 is a diagram for explaining an implementation example of action policy patterning according to an embodiment. FIG. 11 is a flowchart for explaining patterning of action policies according to an embodiment; 10 is a flowchart illustrating an operation of an action policy checking unit according to the embodiment. 5 is a flowchart illustrating an operation of an environmental change observing unit according to the embodiment. 10 is a flowchart for explaining an operation of an operation parameter proposing unit according to the embodiment. 10 is a flowchart illustrating an operation of an action policy patterning unit according to the embodiment. 10 is a flowchart illustrating an operation of an action policy score estimation unit according to the embodiment. FIG. 2 is a hardware configuration diagram showing an example of a computer that realizes the functions of the robot and the processing unit of the server of the information processing system 1 according to the embodiment.

Below, a preferred embodiment of the present disclosure will be described in detail with reference to the attached drawings. In this specification and drawings, components having substantially the same functional configuration will be denoted by the same reference numerals to avoid duplicated explanations. The explanation will be given in the following order.

1. Functional block diagram of information processing system 1 1.1. Functional block diagram of robot 2 1.2. Functional block diagram of server 3 1.3. Operation parameters 1.4. Environmental information 1.5. Action policy patterning 1.6. Implementation example of action policy patterning 2. Operation of information processing system 1 2.1. Operation of action policy confirmation unit 13 2.2. Operation of environmental change observation unit 16 2.3. Operation of operation parameter proposal unit 15 2.4. Operation of action policy patterning unit 32 2.5. Operation of action policy score estimation unit 35 3. Effects 4. Hardware configuration

<1. Functional block diagram of information processing system 1>
1 is a functional block diagram of an information processing system 1 according to an embodiment. As shown in FIG. 1, the information processing system 1 includes a robot 2 and a server 3.

In FIG. 1, the robot 2 and the server 3 are connected via a network (not shown). Although one robot 2 is shown in FIG. 1, there may be multiple robots 2. Each of the multiple robots 2 has a control device for the operating parameters of the robot 2.

<1.1. Functional block diagram of robot 2>
A functional block diagram of the control device for the motion parameters of the robot 2 will be described below with reference to FIG.

The robot 2 has a user I/F 11, an operation parameter change unit 12, an action policy confirmation unit 13, an action policy database 14, an operation parameter proposal unit 15, an environmental change observation unit 16, an operation parameter database 17, a control unit 18, an actuator 19, a sensor 20, a recognition unit 21, and an environmental information database 22.

(User I/F 11)
The user I/F 11 is an input/output interface for the control device of the operation parameters of the robot 2, and may be, for example, a computer such as a PDA (Personal Digital Assistant) or a mobile phone. The user I/F 11 accepts a request to change the operation parameters of the robot 2, and outputs the changed operation parameters corresponding to the accepted change request. Examples of the "change request" include "increase the moving speed" and "decrease the transport speed" of the robot 2. The user I/F 11 outputs the changed operation parameters corresponding to such a "change request" to the operation parameter change unit 12. Note that, in FIG. 1, the user I/F 11 outputs the changed operation parameters corresponding to the "change request", but in FIG. 1, it is shown as a "change request" for ease of understanding.

(Operation parameter change unit 12)
The action parameter change unit 12 outputs the changed action parameters (change contents) output from the user I/F 11 to the action policy confirmation unit 13. As an example of changing the action parameters, it is possible to set a certain value or to increase or decrease a certain value. For example, as an example of setting a certain value, "translation speed = slow" may be set. As an example of increasing or decreasing a certain value, "translation speed + = 0.1 m/s" may be set.

An "action policy" is a combination of an "environmental change" and an "action parameter." For example, when the environmental change is "valuables: +4," the action parameter is "translation speed = slow." Another "action policy" is, for example, when the environmental change is "increased people," the action parameter is "slow down the movement speed." This action policy is for making robot 2 move slowly in crowds. Action policies can change depending on people's position, role, and personality, so they can be patterned and grouped.

There may be multiple action policies for each user. For example, when the environmental change is "Strangers: present", the action parameters may be a combination of "audio output = true, indicator light = true". Another example is when the environmental change is "road width = narrow, children: present", the action parameters may be a combination of "distance at which to start dodging = farther, translation speed = slower". The action parameter change unit 12 also receives the proposed action parameters that have been accepted and output from the action parameter suggestion unit 15, and stores them in the action parameter database 17.

Specifically, an action policy is data consisting of a character string or a number sequence. An action policy is made up of a combination of "environmental changes" and "operation parameters", so "environmental changes" are data consisting of "character strings or number sequences", and "operation parameters" are data consisting of "character strings or number sequences that affect the operation of robot 2".

"Environmental change" refers to a change in the environment around robot 2, and may include data on the position of robot 2 and information on time. "Environmental change" may also include semantic information on the location of robot 2, object information, the shape of the travel area, the operation to be performed, and environmental characteristics such as temperature, humidity, and illuminance.

"Environmental changes" are obtained from the time difference of environmental information obtained from all camera images or parts of image frames. "Environmental information" is obtained from sensor information other than camera images, such as LiDAR (Light Detection and Ranging), microphone, temperature and humidity sensor, illuminance sensor, IMU (Inertial Measurement Unit), and wheel encoder.

"Operation parameters" are set as default values when shipped from the factory. "Operation parameters" are not linked to "environmental changes" and exist as operational parameters alone. "Operation parameters" can be additionally input/modified by the user after shipping from the factory.

Note that the robot 2 can also add/modify movement parameters, but since appropriate movement parameters are thought to differ depending on the characteristics of the user (position, role, personality), the movement parameters may be linked to some input, such as user input or environmental changes. This allows the robot 2 to set appropriate movement parameters according to the user.

(Operation parameter database 17, etc.)
The operation parameter database 17 outputs the proposed operation parameters stored by the operation parameter changing unit 12 and accepted to the control unit 18. The control unit 18 is a control device that controls each actuator 19 of the robot 2. The control unit 18 outputs the operation parameters output from the operation parameter database 17 to the corresponding actuators 19. The actuators 19 control each unit of the robot 2 corresponding to the actuators 19 based on the received operation parameters.

(Sensor 20, etc.)
The sensor 20 measures information related to the environment of the robot 2. The recognition unit 21 receives the information related to the environment measured by the sensor 20 and recognizes the environmental information. The recognition unit 21 may recognize the environmental information together with information related to the input environment. The recognition unit 21 stores the recognized environmental information in the environmental information database 22. The environmental information database 22 outputs the stored environmental information to the environmental change observation unit 16.

(Environmental change observation unit 16)
The environmental change observing unit 16 observes an environmental change based on the environmental information output from the environmental information database 22, and outputs a notification that an environmental change has occurred to the action policy confirming unit 13 and the operation parameter proposing unit 15.

"Environmental change" refers to a change in the environment around robot 2, for example, the environment of robot 2 changing to a certain value (the previous value is irrelevant), environmental information exceeding/falling below a threshold, the amount of change in environmental information exceeding/falling below a threshold, etc.

The environment may change to a certain value, for example, if it changes from "Strangers: None" to "Strangers: Present," or from "Road width: Normal, Wide" to "Road width: Narrow."

For example, environmental information exceeding/falling below a threshold value could mean "the distance to valuables is less than 1.0 m" or "the usage time exceeds six months."

An example of a change exceeding/falling below a threshold would be when the number of children changes from "children (usually) 1" to "children: 5," with the change of +4 exceeding the threshold.

(Action Policy Checking Unit 13)
When an environmental change is observed, the action policy checking unit 13 asks the user whether the change in the operating parameters is caused by the environmental change. When the change in the operating parameters is caused by the environmental change, the action policy checking unit 13 acquires an "action policy" having a combination of the "environmental change" and the "operation parameters (of the change request)" and saves it in the action policy database 14 of the robot 2. When the change in the operating parameters is caused by the environmental change and the reason for the change is obtained, the action policy checking unit 13 adds the reason for the change to the "action policy" and saves it as such. When the change in the operating parameters is caused by the environmental change, the action policy checking unit 13 updates the environmental change in the user's action policy to the environmental change that is the cause.

The action policy pattern to which the updated user's action policy belongs has an action policy score (similar to the action policy score in step S42 of FIG. 9). Questions are posed to the user in descending order of the action policy scores.

(Action Policy Database 14)
When a user's action policy is updated by the action policy confirmation unit 13, the updated user's action policy is stored in the action policy database 14. In addition, when the action policy results are transmitted to the server 3 and an action policy score is received from the server 3, a new action policy is stored or the score of an action policy already stored is updated based on the contents of the action policy.

In other words, the action policy database 14 stores the operating parameters of the robot that are changed, including the environmental change, when there is an environmental change. Also, the action policy score from the server 3 is added to the action policy and stored in the action policy database 14.

The data format stored in the action policy database 14 of each robot 2 is a collection of [action policy, number of times adopted, number of times rejected, score].

The increase in the number of adoptions/rejections is performed by the action policy confirmation unit 13 and the operation parameter proposal unit 15. The number of adoptions and rejections is used by the action policy patterning unit 32 of the server 3 when acquiring the action policy performance of the user.

(Operation Parameter Proposal Unit 15)
When there is an environmental change, the operation parameter suggestion unit 15 acquires operation parameters to be changed and applied to the robot 2 stored in the action policy database 14. When the operation parameter suggestion unit 15 accepts the proposal of the proposed operation parameters, it outputs the proposed operation parameters to the operation parameter change unit 12 and makes a request to change the operation parameters.

The operation parameters acquired by the operation parameter suggestion unit 15 are the operation parameters of the pattern of the action policy to which the user's action policy belongs. Suggestions to the user are made for operation parameters of patterns whose relevance to the user's action policy is equal to or greater than a threshold value.

The operation parameter suggestion unit 15 increases the number of times the proposed operation parameter is adopted when the proposed operation parameter is accepted. In addition, the operation parameter suggestion unit 15 increases the number of times the proposed operation parameter is rejected when the proposed operation parameter is not accepted.

The action policy pattern to which the user's action policy belongs has an action policy score. The action parameter suggestion unit 15 suggests to the user the action parameters obtained in descending order of the action policy scores.

<1.2. Functional block diagram of server 3>
The server 3 includes an action policy result database 31 , an action policy patterning unit 32 , a user database 33 , a pattern database 34 , and an action policy score estimation unit 35 .

(Action policy performance database 31)
The action policy result database 31 stores the action policy results stored in the action policy database 14 of each robot 2. The data format of the action policy result data is a set of [action policy, user, number of times adopted, number of times rejected].

(User database 33)
The user database 33 stores user data. The data format of the user data is a set of [pattern, belonging users (multiple)].

(Pattern Database 34)
The pattern database 34 stores pattern data. The format of the pattern data is a set of [user, belonging pattern (plural)].

(Action Policy Patterning Unit 32)
The action policy patterning unit 32 patterns the action policies based on the data stored in the action policy result database 31, the user database 33, and the pattern database 34. The patterning of the action policies will be described later.

An "action policy pattern" is a collection or group of "action policies." For example, in the case of (a pattern of a family with children), if the environmental change is "children: present," the action parameter is "translational speed = slow," and if the environmental change is "children: absent," the action parameter is "translational speed = fast." For example, in the case of (a pattern of a factory where people coexist), if the environmental change is "low illumination," the action parameters are "translational speed = fast, indicator light = false," and if the environmental change is "people: present," the action parameters are "translational speed = slow, indicator light = true, audio output = true."

(Action Policy Score Estimation Unit 35)
The action policy score estimation unit 35 estimates the score of the action policy based on the data stored in the user database 33 and the pattern database 34. The estimation of the score of the action policy will be described later.

In FIG.
Data format of "change request"/"change content"/"change proposal" = a collection of "change content of operation parameters".
- Data format of "Action policy confirmation" = one of the following - Is the "change" due to an "environmental change"?
- What are the “changes”?
It is.
・"Answer" data format = Either of the following ・"YES" or "NO"
・"Free response"
It is.
- "Accept/Reject" data format = "YES"/"NO"
It is.
・Data format of "Environmental changes" = Array of "Environmental changes".
Data format of "action policy performance" = a set of [action policy, number of adoptions, number of rejections].
Data format of "action policy score" = a set of [action policy, score].

1.3. Operation parameters
2 is a diagram showing an example of the motion parameters of the robot 2 according to the embodiment. As shown in Fig. 2, for the motion parameter "Whether to pause at a corner and turn on the spot", an example of data is "Turn method = pause and turn on the spot", a variation of the value is "pause and turn on the spot, pass through without stopping", and a data type is "integer type, etc."

For the "translation/rotation speed" operation parameters, examples of data include "translation speed = 0.8 m/s, rotation speed = 0.5 rad/s, translation speed = fast, rotation speed = slow," and data types include "floating point type, integer type, etc. (fast = 0, standard = 1, etc.)."

For the "translational/rotational acceleration" motion parameter, examples of data include "translational acceleration = 0.3 m/s2, rotational acceleration = 0.2 rad/s2, translational acceleration = agile, rotational acceleration = smooth," and data types include "floating point type, integer type, etc. (agile = 0, standard = 1, etc.)." The motion parameters "translational/rotational speed" and "translational/rotational acceleration" are classified as "speed."

For the operating parameter "maximum deviation from a given route," examples of data include "maximum deviation = 2.0 m, maximum deviation = wide," and data types include "floating point type, integer type, etc. (narrow = 0, standard = 1, wide = 2, etc.)."

For the operation parameter "distance at which to start avoiding obstacles," examples of data include "distance at which to start avoiding obstacles = 3.0 m, distance at which to start avoiding obstacles = closer," and data types include "floating point type, integer type, etc. (farther = 0, standard = 1)."

For the operation parameter "distance when passing next to an obstacle," examples of data include "passing offset distance = 0.5 m, passing offset distance = just barely," and data types include "floating point type, integer type, etc. (farther = 0, standard = 1)."

For the action parameter "Avoid obstacles?", an example of data is "Avoid = false (Do not avoid = stop and wait)" and an example of the data type is "Boolean type, etc.".

As for the behavior parameters of "replacing the above three types of 'obstacles' with 'objects with specific attributes'", an example of data is "same as the above three", other variations include "specific attributes = known people, strangers, children, adults, elderly people, fragile items, dangerous items, food, valuables, etc.", and the data type is "same as the above three". Note that the classification of behavior parameters of "distance at which to start avoiding obstacles", "distance when passing by an obstacle", "whether to avoid obstacles", and "replacing the above three types of 'obstacles' with 'objects with specific attributes'" are classified as "avoidance behavior".

For the operation parameter "Should sound be produced during operation?", an example of data is "audio output = false" and an example of a data type is "bool type, etc." The classification of the operation parameter "Should sound be produced during operation?" is classified as "audio."

For the operation parameter "Should the indicator light or direction of travel be displayed during operation?", an example of data is "indicator light = true, direction of travel display = false", and the data type is "Boolean, etc.". The classification of the operation parameter "Should the indicator light or direction of travel be displayed during operation?" is classified as "indicator light".

<1.4. Environmental information>
3 is a diagram showing an example of the environmental information of the robot 2 according to the embodiment. As shown in FIG. 3, the environmental information of the "type of place" is, for example, "type of current location = office"", with value variations of "office, warehouse, loading entrance, hallway, kitchen, dining room, bedroom" and data types of "integer type, etc.: office = 1, running = 2...".

As for the environmental information of "place attributes", examples of data include "should be quiet = true, should be clean = false...", and value variations include "should be quiet, should be clean, should be careful about safety", and data types include "Boolean associative array, etc.". The classification of environmental information of "place attributes" is categorized as "semantic information".

As for environmental information such as "presence or absence of objects with a particular attribute," "number of objects with a particular attribute," "proportion of objects with a particular attribute (in the same category)," and "nearest distance of objects with a particular attribute," examples of data include "Children: Presence = Yes, Number = 3, Proportion = 60%, Distance = 1.2 m, Elderly: Presence = Yes, Number = 2, Proportion = 40%, Distance = 3.5 m, Fragile items: Presence = Yes, Number = 3, Proportion = 30%, Distance = 1.4 m." Other variations include "Attributes: known people, strangers, children, adults, elderly people, fragile items, dangerous items, food, valuables, presence/absence: yes/no."

For "presence or absence of objects with a specific attribute," the data type is "Boolean, etc.", for "number of objects with a specific attribute," the data type is "floating point, etc.", for "proportion of objects with a specific attribute (in the same category)," the data type is "floating point, etc.", and for "nearest distance of objects with a specific attribute," the data type is "floating point, etc." Note that the classification of environmental information for "presence or absence of objects with a specific attribute," "number of objects with a specific attribute," "proportion of objects with a specific attribute (in the same category)," and "nearest distance of objects with a specific attribute" are classified as "object information."

For the environmental information of "driving area attributes", examples of data include "road is narrow = true, visibility around corners is good = false, floor is slippery = false", and value variations include "road is narrow, visibility around corners is good, floor is slippery", and data types include "bool-type associative array, etc.".

For the environmental information "Characteristics of the driving area", examples of data include "Road width = 2.3 m, Friction coefficient = XXX", and data types include "Floating point type, etc.". The classification of environmental information for "Attributes of the driving area" and "Characteristics of the driving area" is categorized as "Shape of the driving area".

For the environmental information of "handled object attributes", examples of data include "load is dangerous = true, operation target is fragile = false", and a data type is "Boolean associative array, etc." The classification of environmental information of "handled object attributes" is categorized as "operation content".

For the "usage time" environmental information, an example of data is "usage time = 124 days" and an example of a data type is "floating-point associative array, etc." The classification of "usage time" environmental information is "elapsed time."

For "season, month" environmental information, an example of data is "current season = summer, month = 7" and an example of a data type is "integer associative array, etc." The classification of "season, month" environmental information is classified as "season."

For the environmental information in "Environmental Information", examples of data include "Temperature = 21.4°C, Humidity = 45%, Illuminance = 184 lx, Temperature = High, Humidity = Low, Illuminance = Low", and data types include "floating-point type, integer type associative array, etc." The classification of environmental information in "Environmental Information" is "Environmental Characteristics".

1.5. Action Policy Patterning
Next, the action policy patterning in the action policy patterning unit 32 in the server 3 will be described.

FIG. 4 is a diagram for explaining patterning in server 3 according to an embodiment. As shown in FIG. 4, each user has a pattern to which it belongs and a set of action policies. Each pattern has a user to which it belongs and a set of action policies. It is assumed that the action policy of a certain user can be expressed as a set of multiple patterns.

For example, user A has action policy X and belongs to pattern "1" with action policy X. User B has action policy X, action policy Y, and action policy Z, and belongs to pattern "1" with action policy X and pattern "2" with action policy Y and action policy Z. User C has action policy Y, action policy Z, and action policy W, and belongs to pattern "2" with action policy Y and action policy Z, and pattern "3" with action policy Z and action policy W.

For "pattern updates," patterns that have common elements in the action policies of the users who belong to the group are searched for, and the action policies that are included as patterns are updated.

For "updating a user," it calculates which set of action policies represents the user's action policy with the highest degree of match, and updates the pattern to which the user belongs to with the highest degree of match.

<1.6. Example of action policy pattern implementation>
5 is a diagram for explaining an implementation example of action policy patterning according to an embodiment. In Fig. 5, the action policy data up to now is expressed in a matrix D. Each row of the matrix D indicates which action policy the user has.

As shown in Figure 5, user A has action policy X, user B has action policy X, action policy Y, and action policy Z, and user C has action policy Y, action policy Z, and action policy W (also see Figure 4).

The configuration patterns of each user are represented by a matrix U. Each row of U indicates which pattern a user is configured with. As shown in Figure 5, user A has pattern "1", user B has pattern "1" and pattern "2", and user C has pattern "2" and pattern "3" (also see Figure 4).

The action policies for each pattern are represented by a matrix P. Each row of P indicates which action policies the pattern is composed of. As shown in Figure 5, pattern "1" has action policy X, pattern "2" has action policy Y and action policy Z, and pattern "3" has action policy Z and action policy W (also see Figure 4).

Matrix U, matrix P, and matrix D have the relationship UP=D. Action policies are patterned in the following order:

FIG. 6 is a flowchart for explaining the patterning of action policies according to an embodiment. First, matrix U is initialized with random numbers (step S1). Next, a matrix equation is solved to obtain matrix P (step S2). Next, matrix U that is close to UP=D is obtained using the least squares method (step S3). Then, a determination is made as to whether matrix U has been obtained (step S4). If matrix U has not been obtained (No in step S4), the process returns to step S2. If matrix U has been obtained (Yes in step S4), the process ends.

2. Operation of Information Processing System 1
<2.1. Operation of action policy check unit 13>
7 is a flow chart for explaining the operation of the action policy checking unit 13 according to the embodiment. As shown in Fig. 7, the action policy checking unit 13 judges whether or not an environmental change has occurred from the environmental change observing unit 16 (step S21).

If there is no environmental change in step S21 (NO in step S21), the process proceeds to step S27. If there is an environmental change in step S21 (YES in step S21), the action policy that has undergone the environmental change ("environmental change" + "changed operating parameters") is obtained (step S22).

Next, the action policy confirmation unit 13 sorts the obtained action policies in descending order of the action policy score (step S23). This action policy score is the score added to the action policy. The action policy score is stored in the action policy database 14 together with the action policy.

The action policy confirmation unit 13 asks the user whether the "changes" (changes to the operating parameters) of the action policies for all action policies are due to "environmental changes" (step S24). It then determines whether the user answers the question with "YES" (step S25).

If the answer is "YES" (YES in step S25), the process proceeds to step S28. If the answer is not "YES" (NO in step S25), the user is asked the reason for the change (step S26).

It is determined whether "environmental change" is obtained as the answer to the question in step S26 (step S27). If "environmental change" is not obtained as the answer (NO in step S27), the process ends. If "environmental change" is obtained as the answer (YES in step S27), the number of times the combination of "change content" and "environmental change" has been adopted is increased by one (step S28). This "number of times adopted" is used as an achievement value in the action policy patterning unit 32 of the server 3.

<2.2. Operation of the environmental change observation unit 16>
8 is a flow chart for explaining the operation of the environmental change observing section 16 according to the embodiment. As shown in Fig. 8, the environmental change observing section 16 acquires environmental information at the current time (step S31).

Next, for a given time difference, environmental information for the current time minus the time difference is acquired (step S32), and the difference in the environmental information is extracted (step S33). Next, the environmental change observation unit 16 determines whether there is a difference in the environmental information (step S34).

If it is determined that there is no difference (NO in step S34), the process returns to step S32. If it is determined that there is a difference (YES in step S34), it is added to the environmental change set (step S35), and the process proceeds to step S36.

In step S36, the set of environmental changes added in step S35 is output (step S36), and the process ends.

<2.3. Operation of the operation parameter proposing unit 15>
FIG. 9 is a flowchart for explaining the operation of the operation parameter proposing unit 15 according to the embodiment.

As shown in FIG. 9, the operation parameter suggestion unit 15 acquires an action policy including the relevant "environmental change" from the action policy database 14 (step S41). As a result, since the action policy has an "environmental change" and an "operation parameter", the operation parameter suggestion unit 15 acquires the operation parameters to be changed and applied to the robot 2. Next, the operation parameter suggestion unit 15 sorts the acquired action policies in descending order of the action policy scores (step S42).

Next, for all action policies whose relevance is equal to or greater than the threshold, the user is asked (suggested) whether to apply the "changes" due to the "environmental changes" (step S43), and it is determined whether the answer to the question is "YES" (step S44).

If the answer is "YES" (YES in step S44), the number of times the combination of "change content" and "environmental change" is adopted is increased (step S45), the "change content" is sent to the operation parameter change unit 12 (step S46), and the process ends.

If the answer is "NO" (NO in step S44), the number of times "Changes" and "Environmental changes" are rejected is increased (step S47), and the process ends.

<2.4. Operation of the action policy pattern generator 32>
FIG. 10 is a flowchart for explaining the operation of the action policy patterning unit 32 according to the embodiment.

As shown in FIG. 10, the action policy patterning unit 32 acquires a pattern (step S51). Then, for each acquired pattern, steps S52 and S53 are performed. In step S52, the action policy track record of the user is acquired. The action policy of each user is linked to the data of "number of times adopted" and "number of times rejected" sent from the robot 2 of each user. The action policy patterning unit 32 uses the data of "number of times adopted" and "number of times rejected" as the action policy track record. In step S53, the common part is extracted to create a new pattern.

Next, the action policy patterning unit 32 obtains users from the user database 33 (step S54) and performs steps S55 to S57 for each user.

In step S55, the action policy results are obtained from the action policy database 14. In step S56, a calculation is made as to which set of patterns the action policy results match best when expressed as a set. In step S57, the set with the highest match is treated as the new pattern to which the action policy results belong, and the process ends.

<2.5. Operation of the action policy score estimation unit 35>
FIG. 11 is a flowchart for explaining the operation of the action policy score estimation unit 35 according to the embodiment.

As shown in FIG. 11, the action policy score estimation unit 35 acquires users from the user database 33 (step S61) and performs the processes of steps S62 to S64 for each user.

In step S62, the score of the action policy is initialized. In step S63, the user's belonging pattern is obtained. In step S64, for each belonging pattern, the score of the action policy included in the belonging pattern is increased.

Then, the action policy score is output to the action policy database 14 of the user's robot 2 (step S65), and the process ends.

<3. Effects>
Therefore, according to the information processing system 1 of the embodiment, by proposing operation parameters in accordance with environmental changes, the robot 2 always operates in a manner appropriate to the situation, thereby improving efficiency and comfort.

In addition, the information processing system 1 according to the embodiment makes suggestions based on the characteristics of the user, so the user's comfort is not compromised.

4. Hardware Configuration
Fig. 12 is a hardware configuration diagram showing an example of a computer that realizes the calculation unit of the robot 2 and the server 3 of the information processing system 1 according to the embodiment. The computer that realizes the calculation device of the robot 2 and the server 3 according to the embodiment described above is realized by a computer 1000 having a configuration as shown in Fig. 12, for example. Fig. 12 is a hardware configuration diagram showing an example of the computer 1000 that realizes the function of the calculation device. The computer 1000 has a CPU 1100, a RAM 1200, a ROM (Read Only Memory) 1300, a HDD (Hard Disk Drive) 1400, a communication interface 1500, and an input/output interface 1600. Each part of the computer 1000 is connected by a bus 1050.

The CPU 1100 operates based on the programs stored in the ROM 1300 or the HDD 1400 and controls each part. For example, the CPU 1100 loads the programs stored in the ROM 1300 or the HDD 1400 into the RAM 1200 and executes processes corresponding to the various programs.

The ROM 1300 stores boot programs such as the BIOS (Basic Input Output System) that is executed by the CPU 1100 when the computer 1000 starts up, as well as programs that depend on the hardware of the computer 1000.

HDD 1400 is a computer-readable recording medium that non-temporarily records programs executed by CPU 1100 and data used by such programs. Specifically, HDD 1400 is a recording medium that records application programs related to the present disclosure, which are an example of program data 1450.

The communication interface 1500 is an interface for connecting the computer 1000 to an external network 1550 (e.g., the Internet). For example, the CPU 1100 receives data from other devices and transmits data generated by the CPU 1100 to other devices via the communication interface 1500.

The input/output interface 1600 is an interface for connecting the input/output device 1650 and 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. The CPU 1100 also transmits data to an output device such as a display, a speaker, or a printer via the input/output interface 1600. The input/output interface 1600 may also function as a media interface that reads programs and the like recorded on a specific recording medium. Examples of media include optical recording media such as DVDs (Digital Versatile Discs) and PDs (Phase change rewritable Discs), magneto-optical recording media such as MOs (Magneto-Optical Disks), tape media, magnetic recording media, and semiconductor memories.

The HDD 1400 stores the programs and data related to the present disclosure. The CPU 1100 reads and executes the program data 1450 from the HDD 1400, but as another example, the CPU 1100 may obtain these programs from other devices via the external network 1550.

The above describes in detail preferred embodiments of the present disclosure with reference to the attached drawings, but the technical scope of the present disclosure is not limited to such examples. It is clear that a person with ordinary knowledge in the technical field of the present disclosure can conceive of various modified or revised examples within the scope of the technical ideas described in the claims, and it is understood that these also naturally fall within the technical scope of the present disclosure.

Furthermore, the effects described in this specification are merely descriptive or exemplary and are not limiting. In other words, the technology disclosed herein may achieve other effects that are apparent to a person skilled in the art from the description in this specification, in addition to or in place of the above effects.

The present technology can also be configured as follows.
(1)
Obtaining the operating parameters applied to the robot when there is an environmental change;
Suggesting the obtained operating parameters to a user;
An information processing method for applying the proposed operation parameters to the robot when the proposed operation parameters are accepted.
(2)
The information processing method according to (1), wherein the user's action policy includes the environmental change and the operation parameters.
(3)
Obtaining the motion parameters of the robot includes:
The information processing method according to (1) or (2), further comprising obtaining operation parameters of a pattern of an action policy to which the action policy of the user belongs.
(4)
The proposal to the user is:
The information processing method according to (1), wherein the processing is performed for operation parameters of a pattern having a degree of relevance to the user's action policy equal to or greater than a threshold value.
(5)
The information processing method according to (4), further comprising increasing the degree of association when the proposed operation parameter is accepted.
(6)
The information processing method according to (4), further comprising decreasing the degree of association when the proposed operation parameter is not accepted.
(7)
A pattern of action policies to which the action policy of the user belongs has a score of the action policy;
Proposing the obtained operating parameters to a user includes:
The information processing method according to (3), further comprising: suggesting the acquired operation parameters to a user in descending order of the scores of the action policies.
(8)
The information processing method according to (2), further comprising observing the environmental change.
(9)
If the environmental change is observed, asking the user whether the change in the operating parameter is due to the environmental change;
The information processing method according to (8), further comprising updating the environmental change in the user's action policy to the causative environmental change if the change in the operating parameter is due to the environmental change.
(10)
The pattern of action policies to which the updated user's action policy belongs has an action policy score;
The information processing method according to (9), wherein the questions to the user are asked in descending order of the scores of the action policies.
(11)
The information processing method according to any one of (3) to (7), wherein the pattern of action policies to which the action policy of the user belongs is a pattern having a highest degree of match between the action policy of the user and the action policy of the pattern.
(12)
An acquisition unit that acquires operation parameters to be applied to the robot when there is an environmental change;
a suggestion unit that suggests the acquired operation parameters to a user;
and an application unit that applies the proposed operation parameters to the robot when the proposal for the proposed operation parameters is accepted.
(13)
On the computer,
When there is an environmental change, the operating parameters applied to the robot are acquired,
having a user suggest the acquired operating parameters;
A program for applying the proposed operation parameters to the robot when the proposal for the proposed operation parameters is accepted.

Reference Signs List 1 Information processing system 2 Robot 3 Server 11 User I/F
REFERENCE SIGNS LIST 12 Operation parameter change unit 13 Action policy confirmation unit 14 Action policy database 15 Operation parameter proposal unit 16 Environmental change observation unit 17 Operation parameter database 18 Control unit 19 Actuator 20 Sensor 21 Recognition unit 22 Environmental information database 31 Action policy result database 32 Action policy patterning unit 33 User database 34 Pattern database 35 Action policy score estimation unit

Claims (13)

Obtaining the operating parameters applied to the robot when there is an environmental change;
Suggesting the obtained operating parameters to a user;
An information processing method for applying the proposed operation parameters to the robot when the proposed operation parameters are accepted. 2. The information processing method according to claim 1, wherein the user's action policy includes the environmental changes and the operating parameters. Obtaining the motion parameters of the robot includes:
3. The information processing method according to claim 2, further comprising acquiring operation parameters of a pattern of an action policy to which the action policy of the user belongs. The proposal to the user is:
The information processing method according to claim 1 , wherein the method is performed for operation parameters of a pattern having a degree of association with the user's action policy equal to or greater than a threshold value. The information processing method according to claim 4 , further comprising increasing the degree of association when the proposed operation parameter is accepted. The information processing method according to claim 4 , further comprising the step of decreasing the degree of association when the proposed operation parameter is not accepted. A pattern of action policies to which the action policy of the user belongs has a score of the action policy;
Proposing the obtained operating parameters to a user includes:
The information processing method according to claim 3 , wherein the acquired operation parameters are proposed to the user in descending order of the scores of the action policies. The information processing method according to claim 2 , further comprising observing the environmental change. If the environmental change is observed, asking the user whether the change in the operating parameter is due to the environmental change;
9. The information processing method according to claim 8, further comprising updating the environmental change in the user's action policy to the causative environmental change if the change in the operating parameter is due to the environmental change. The pattern of action policies to which the updated user's action policy belongs has an action policy score;
The information processing method according to claim 9 , wherein the questions to the user are posed in descending order of the scores of the action policies. 4. The information processing method according to claim 3, wherein the pattern of action policies to which the action policy of the user belongs is a pattern having a highest degree of match between the action policy of the user and the action policy of the pattern. An acquisition unit that acquires operation parameters to be applied to the robot when there is an environmental change;
a suggestion unit that suggests the acquired operation parameters to a user;
and an application unit that applies the proposed operation parameters to the robot when the proposal for the proposed operation parameters is accepted. On the computer,
When there is an environmental change, the operating parameters applied to the robot are acquired,
having a user suggest the acquired operating parameters;
A program for applying the proposed operation parameters to the robot when the proposal for the proposed operation parameters is accepted.

Images