JP2020113025A - Space control system - Google Patents

Abstract

To provide a space control system for creating an environment corresponding to each emotion of a user.SOLUTION: A space control system 1 comprises an environment generation device 10, an agent robot 50, and a control device 20. The environment generation device 10 can generate one or more environments in a subject space S. The agent robot 50 embodies an agent executing operations corresponding to emotion causing to arise in a subject user 5. The control device 20 controls the environment generation device 10 so as to generate a prescribed environment corresponding to the operations of the agent.SELECTED DRAWING: Figure 1

Description

The present disclosure relates to spatial control systems.

Conventionally, a device that reproduces the environment one has experienced has been developed. For example, Patent Document 1 (Japanese Patent Laid-Open No. 2003-299013) discloses an experience information reproduction device that allows a person who experiences the experience to re-experience it with a sense of reality.

However, how to feel about the environment varies greatly depending on the emotion of the user. Therefore, it is necessary to create an environment according to the emotion of each user.

The present disclosure aims to provide a spatial control system that is effective in creating an environment according to individual emotions.

An air conditioning control system according to a first aspect is an environment generation device capable of generating one or more environments in a target space, an actuator that realizes an agent that performs an action according to an emotion that a target user tries to cause, and an agent. And a control device for controlling the environment generation device so as to generate a predetermined environment according to the operation of. Therefore, it is effective to create an environment according to the emotion of each user.

In the air conditioning control system according to the second aspect, the actuator is at least one of an air conditioner, a robot, a color changing device, a rhythm device, a light amount changing device, a voice device, an odor generating device, a projector, and a display device. Therefore, the agent realized by the actuator can realize various actions according to the emotion of the user.

In the air conditioning control system according to the third aspect, the agent includes an interface having a biological element. Therefore, emotional interaction between the agent and the user is facilitated.

In the air conditioning control system according to the fourth aspect, the actuator can realize an agent that executes a plurality of operations, the environment generation device can generate a plurality of environments, and the plurality of operations and the plurality of environments are associated with each other. The control device controls the environment generation device so as to generate a predetermined environment based on the correspondence between the plurality of operations and the plurality of environments. Therefore, the agent can perform various actions according to the emotion of the user, and can generate various environments according to the action.

An air conditioning control system according to a fifth aspect includes a plurality of environment generation devices, and the control device controls the plurality of environment generation devices so as to generate a predetermined environment according to the operation of the agent. Therefore, it is possible to generate an effective environment according to the emotion of the user.

In the air conditioning control system of the sixth aspect, the control device causes the environment generation device to generate a predetermined environment in synchronization with the operation of the agent, and then temporarily or intermittently stops the generation of the environment by the environment generation device, The actuator temporarily or intermittently stops the operation of the agent. Therefore, in order to suppress the harmful effects of using a conventional agent with high tangibility for a long time, for example, the risk that the user gets tired of its existence or feels annoying, an environment that is effective for the user Can be generated.

In the air conditioning control system according to the seventh aspect, the actuator stops the operation of the agent while the control device causes the environment generation device to generate a predetermined environment in synchronization with the operation of the agent.

In the air conditioning control system of the eighth aspect, the environment generation device is a device that stimulates the user's sense in the target space.

In the air conditioning control system according to the ninth aspect, the actuator is a device that evokes at least one of the five senses of the user by the action of the agent.

In the air conditioning control system of the tenth aspect, the environment generation device is an air conditioner, a sound device, a lighting device, an odor generating device, or a projector.

An air conditioning control system according to an eleventh aspect includes an input device that acquires input information. The actuator realizes an agent that performs an action according to the emotion that the user wants to cause based on the input information. The input information includes information specified based on an onomatopoeia or an onomatopoeia word, or an event corresponding to the onomatopoeia word or an onomatopoeia word. Since it is highly likely that information close to the actual user's emotions will be obtained, it is effective in creating an environment according to the user's emotions.

It is a schematic diagram for demonstrating the whole structure of a space control system. It is an external view of an agent. It is a functional block diagram of an agent. It is a functional block diagram of a control device. It is a schematic diagram for explaining the information stored in the storage unit of the control device. It is a flow chart for explaining operation of a space control system. It is explanatory drawing of operation|movement of a space control system. It is explanatory drawing of operation|movement of a space control system. It is explanatory drawing of operation|movement of a space control system. It is explanatory drawing of an air sensation agent. It is an upper perspective view of an agent. It is a lower perspective view of an agent. It is a front view of an agent. It is a front view after operation of an agent. It is a top view of an agent. It is a bottom view of an agent.

(1) Space control system (1-1) Outline of space control system In recent years, agents such as anthropomorphic robots have been developed that make people feel a high affinity with humans. However, when a person is in contact with such an agent for a long time, he or she becomes tired of the existence of the agent, and it is difficult to maintain the effect for a long time. A space control system according to the present disclosure is a space production that softens the atmosphere of a place casually by making the user have the impression that an agent mediating the user and the environment generation device controls the environment in the target space. I do.

Note that the agent in the present disclosure is explicitly expressed by an actuator. The agent includes an interface having biological elements that include anthropomorphic elements in its shape and movement. An interface having a biological element is a physical form (humanoid, animal, plant type, a form imitating a predetermined character, etc.), a human or animal voice or action, and an electronic display of these. Images, sounds, etc.

The agent is an artifact that mediates between the user and the environment generation device. Agents are not only biological robots, but also physical stimuli that make users feel biological existence in some form, such as light and wind presented in a rhythm based on 1/f fluctuations often found in nature. Good. The agent can express a highly explicit emotional expression similar to a living thing, such as a smile expressing a pleasant emotion, by a change in shape or movement. As a result, it becomes possible to bring out the high acceptability and affinity of the user for the environmental control mediated by the agent. Therefore, realization of an agent is effective in creating an environment according to the emotion of each user.

The actuator is, for example, an air conditioner, a robot, a color changing device, a rhythm device, a light amount changing device, a voice device, an odor generating device, a projector, a display device, or the like. The actuator acquires information indicating the estimated emotional state of the user. In the estimation of the emotional state of the user, the actuator itself may have estimation means, or information indicating the emotional state may be acquired from an external device. The emotional state of the user can be inferred from the user's action on the agent, for example. As a method of estimating the emotional state, the emotion of the user may be estimated from the facial expression of the user captured by the camera.

To realize an agent by an actuator means that the actuator operates a device such as a robot equipped with biological elements itself as an agent, generates and outputs the agent by electronically displayed images and sounds, temperature, humidity It also includes forming a predetermined air sensation by air conditioning such as airflow, and forming a predetermined air sensation that stimulates hearing, smell, sight, touch, etc. (sound, smell, light, touch, wind). The actuator may also serve as an environment generation device described later.

The space control system according to the present disclosure includes an actuator that realizes an agent that gives a strong anthropomorphic impression as an interface for space production, and an environment generation device (for example, a projector) that produces an atmosphere of space. The actuator acquires information indicating the emotional state of the user. For example, when it is estimated that the user has an uneasy feeling, the actuator determines, based on the guess, that the user wants to cause an emotion, for example, to give a sense of security, and performs an action according to the determination. Execute. As a result, an affinity can be drawn between the agent and the user. Then, by operating the environment generation device so as to be linked to the operation of the agent, the sense of the user is stimulated, and further affinity is drawn between the user, the agent, and the environment generation device.

After that, the agent may change the form (for example, the movement is stationary) so as not to give an anthropomorphic impression, and only the environment generation device may continue the same movement. That is, after the user strongly recognizes and remembers the existence of the agent, the biological characteristics of the agent may be attenuated by a method such as stopping the operation of the agent itself. By this processing, it is possible to continue only the operation of the environment generation device while the user holds the memory of the agent. As a result, it becomes possible to create the presence of the agent to the extent that the habituation does not proceed, and it is possible to reduce the annoyance that the highly visible agent always exists in the environment.

The configuration and operation of the space control system according to the embodiment will be described below.

(1-2) Configuration of Space Control System As shown in FIG. 1, the space control system 1 according to the present embodiment includes an agent robot 50, an environment generation device 10, and a control device 20. The space control system 1 is arranged in the target space S and generates an environment according to the emotion of the target user 5.

(1-2-1) Agent Robot FIG. 2 shows an external view of the agent robot 50. As shown in the figure, the agent robot 50 is an example of an actuator, and has a round vase-shaped body 501 and a rounded cylindrical head 502 protruding from the center of the body 501. On the side surface of the head 502, eyes that remind the character's face are shown. The face of the character may be projected from the inside by the built-in projector to be reflected on the side surface of the head 502, or the eyes may be directly drawn on the side surface of the head 502. A base surface 503 is provided above the body 501 to surround the head 502. A touch sensor, which will be described later, is arranged on the body 501. When the user 5 touches the body 501, the agent robot 50 causes the head 502 to retract or protrude from the body 501. The touch sensor may be arranged on the head 502 and/or the base 503. In addition, the agent robot 50 does not need to be operated by a touch sensor to perform an operation, and may perform an operation in response to an input from another sensor, a camera, or a microphone. For example, the agent robot 50 can move in synchronization with the user 5, the environment generated by the environment generation device 10 described later, or other devices.

The function of the agent robot 50 will be described with reference to FIG. The agent robot 50 includes a control unit 51, a detection unit 52, an input unit 53, a memory 54, a communication unit 55, an output unit 56, and a power supply 57. The control unit 51 is a processor such as a CPU or DSP. The control unit 51 executes each function according to the program stored in the memory 54. The detection unit 52 is, for example, a capacitance type touch sensor, and detects the presence or absence of contact by the user 5. The touch sensor is arranged on the body 501 of the agent robot 50 shown in FIG. Touch sensors may be disposed on head 502 and/or base surface 503. A sensor (for example, a potentiometer or a pressure sensor button) that detects pressing may be provided instead of the touch sensor. When the touch sensor detects a contact, the control unit 51 controls, for example, a drive unit (not shown) to move the head 502 in FIG. 2 up and down to retract or project the head 502 into the body 501. Let The touch sensor may form an operation unit for executing other operations of the agent robot 50.

The input unit 53 is, for example, a microphone or a camera. The agent robot 50 estimates the emotion of the user 5 and determines the emotion to be caused by the user 5, so that the agent robot 50 acquires input information via the input unit 53. The agent robot 50 acquires input information by, for example, collecting the voice of the user 5 with a microphone and capturing the facial expression and behavior of the user 5 with a camera.

The communication unit 55 is a communication interface that makes a wired or wireless connection with an external device such as the control device 20 described later. The communication unit 55 is, for example, a wireless interface such as an HDMI (registered trademark) terminal, a USB terminal, Bluetooth (registered trademark), and/or Wi-Fi. The output unit 56 is, for example, a speaker or lighting. The speaker is arranged on the bottom portion 504 of the body 501, for example, and outputs a voice from the agent robot 50. The output unit 56 may also include a projector and output an image.

The agent robot 50 may acquire the input information by an onomatopoeia or an onomatopoeia. For example, information such as a smooth feeling (smoothness), a rough feeling (roughness), and a soft feeling (fluffy) such as an onomatopoeia or a mimetic word related to the tactile sensation, which is not necessarily clear in concept, may be input. In this case, as the input means, the voice of the user 5 may be input via the microphone. Further, the input information may be acquired from the finger pressure of the user 5 detected by the touch sensor of the agent robot 50. For example, it is possible to obtain input information such as being frustrated when touching strongly, or having positive emotions when touching for a long time. The onomatopoeia or onomatopoeia is highly likely to be effective as input information for estimating the emotion of the user 5. Therefore, by using an onomatopoeia or an onomatopoeia as input information, it is possible to improve the accuracy of estimating the emotion of the user 5 and effectively generate an environment according to the emotion of the user 5.

The input information is not limited to the direct expression of the onomatopoeia or onomatopoeia by voice or text, and may be, for example, the information specified based on the event corresponding to the onomatopoeia or onomatopoeia. For example, it is possible to let the user 5 select an image or sound that is close to his or her emotions. Alternatively, the input information may be information such as which contact surface the user 5 has selected and how the contact has been made by using a device having a plurality of contact surfaces that give different tactile sensations.

The input information for the agent robot 50 to estimate the emotion of the user 5 may be biometric information of the user 5 (heartbeat, voice, behavior, facial expression recognition, etc.). In this case, any one of a biometric sensor, a camera, a microphone, or a combination thereof may be used as the input means.

The input information may be information that directly indicates the emotion that the user 5 wants to be.

The agent robot 50 estimates the emotion of the user 5 based on the above-mentioned input information, determines the emotion that the user 5 intends to cause, and executes the operation according to the determination. More specifically, the agent robot 50 estimates the emotion of the user 5 from the input information and determines the emotion that the user 5 intends to cause based on the estimation. For example, the agent robot 50 estimates that the user 5 feels anxiety from the input information. In this case, the agent robot 50 determines based on the same guess that the user 5 is caused to have an emotion, for example, a sense of security, and performs an action according to the determination. When the input information is information that directly indicates the emotion that the user 5 wants to be, the agent robot 50 may determine that the input information is the emotion that the user 5 wants to cause.

The actions executed by the agent robot 50 include actions that stimulate the sensation of the user 5, such as actions in response to the emotions that the user 5 intends to cause and outputs of light and sound. Therefore, the agent robot 50 holds the sensory stimulus generation model including various characteristics. The agent robot 50 may hold a sensory stimulus generation model that matches the individual characteristics of the user 5 who have learned in the past. The sensory stimulus generation model includes, for example, a motion (motion of the head 502 of the agent robot 50, etc.) according to an emotion that the user 5 intends to cause, and a motion pattern such as output of light or sound. Based on the sensory stimulus generation model, the agent robot 50 executes the operation of moving the head 502 up and down, the operation of causing a speaker to emit sound, and the operation of emitting light by illumination, as described above. The motion pattern of the agent robot 50 includes all motions recognized by the target user 5. In this way, the agent robot 50 selects and executes the action pattern based on the information in which the emotion that the user 5 tries to cause and the action pattern are associated with each other.

The agent robot 50 further transmits the selected motion information or information that specifies the emotion to be caused by the user 5 to the control device 20 via the communication unit 55.

By the action of the agent robot 50 according to the emotion of the user 5, it is possible to draw an affinity between the user 5 and the agent robot 50, and the user 5 has a strong anthropomorphic impression of the agent robot 50. You can feel emotions.

The sensory stimulus generation model and operation pattern used by the agent robot 50 may be acquired from another device such as a PC or a mobile terminal via the communication unit 55 without being held by the agent robot 50.

(1-2-2) Environment Generation Device The environment generation device 10 is an arbitrary device capable of generating or changing the environment of the target space S to generate a predetermined environment under the control of the control device 20. As a result of the environment generation device 10 generating or changing the environment, the sensation of the user 5 in the target space S is specifically influenced. Specifically, examples of constituent devices of the environment generation device 10 include an air conditioner, an acoustic device, a lighting device, a projector, a speaker, a robot, and an odor generating device. For example, in FIG. 1, the projector as the environment generation device 10 projects a large number of display objects R on the wall surface of the target space S (projection mapping). The display object R is changed in synchronization with the operation of the agent robot 50, as described later. The display object R expresses various actions by changing the number of points, the moving direction, the size, the color, the shape, and the like. Further, the other environment generating apparatus 10 may be operated at the same time, and light, color, sound, odor, wind, or the like may be added or changed according to the display object R.

The environment generation device 10 is independent of the agent robot 50, and the agent robot 50 mediates between the user 5 and the environment generation device 10, and does not have a function of controlling the environment itself. The agent robot 50 and the environment generation device 10 may share some or all of the constituent devices. The agent robot 50 realizes an environment that matches the estimated emotion of the user via the environment generation device 10.

The environment generation device 10 generates or changes the environment based on the environmental conditions classified into a plurality of clusters.

“Environmental conditions” are parameters that characterize physical quantities that have a particular effect on a person's body and/or mind. For example, the environmental condition is defined by physical quantities such as temperature, humidity, wind, image, video, sound, frequency, etc., and the environment generation device 10 operates in accordance with this. Then, the environment generation device 10 generates or changes the environment, so that the human sense is given a specific influence.

The “specific influence” refers to an action that evokes a predetermined sensation in the five senses of the user 5. For example, specific influences include feeling of sensation (sensitivity that enhances sensitivity to forgetfulness in daily life), tension (feeling that someone is watching when doing something), and inclusion. Feeling (a warm and peaceful feeling that envelops your heart), open feeling (feeling like taking a deep breath in a spacious place), feeling of leaving the boat (when you take a new step, you will be closely supported) ), travel feelings (a little lonely but romantic feeling), and any other environmental changes that evoke such sensations. In addition, the specific influence can be expressed in any words, and may be expressed in a generally conceivable term such as “a pleasant environment”, “an environment in which one can concentrate”, or “an environment with a sense of openness”. It may be expressed in a sensory term such as "environment in which air wrapped in a blanket flows," "environment in which party air flows," "environment in which rainbow-colored air flows". Alternatively, the specific influence may be expressed by terms whose meaning is not clear, such as smooth feeling (smoothness), rough feeling (roughness), and soft feeling (fluffy), such as onomatopoeia or mimetic words related to touch. ..

The correspondence between the specific influence and the environmental condition can be defined by aggregating impressions and the like of the user 5 present in the target space S.

(1-2-3) Control Device The control device 20 controls the environment generation device 10 according to the operation information of the agent robot 50 or the information that specifies the emotion that the user 5 tries to cause. The control device 20 is realized by an arbitrary computer. As shown in FIG. 4, the control device 20 includes a storage unit 21, a communication unit 22, a processing unit 23, a control unit 24, and an output unit 25. Here, each of the above functions is realized by reading a program stored in a storage device (ROM, RAM, etc.) into the CPU, GPU, etc. of the computer. However, the control device 20 is not limited to this, and may be realized as hardware using an LSI (Large Scale Integration), an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), or the like.

As the operation information of the agent robot 50, the control device 20 holds the operation pattern of the agent robot 50 in advance in association with the feature of the cluster described later, and selects the feature of the cluster corresponding to the action pattern. Alternatively, the control device 20 may directly acquire the information indicating the emotion that the user 5 wants to cause in the agent robot 50, and select the feature of the cluster based on the information. The environmental conditions corresponding to the characteristics of the selected cluster include at least settings such as an image, video, sound, and lighting that are synchronized with the operation of the agent robot 50. These pieces of information are not limited to the information directly associated with each other like the table, but may be information associated with each other based on an indirect correspondence.

The storage unit 21 stores various kinds of information, and is realized by an arbitrary storage device such as a memory and a hard disk. Here, the storage unit 21 stores the feature of the cluster and the environmental condition in association with each other. Specifically, the cluster is composed of a set of environmental conditions in a space represented by n-dimensional (n is the number of parameters of the environmental conditions) information. Alternatively, the cluster is made up of regions including environmental conditions in a space represented by n-dimensional information. Then, a unique feature is set for each cluster. For example, as shown in FIG. 5, the storage unit 21 stores information such as temperature, humidity, wind, image, video, sound, and frequency as n-dimensional information. These values are grouped into one cluster by a predetermined clustering method, and the characteristics of the cluster are set. Further, the feature of the cluster mentioned here corresponds to the above-mentioned specific influence. In the example shown in FIG. 5, "fun environment" is set as the characteristic of the cluster 1, "concentrated environment" is set as the characteristic of the cluster 2, and "open environment" is set as the characteristic of the cluster 3. In addition, a plurality of environmental conditions belong to each cluster. In the example shown in FIG. 5, the environmental conditions 1 to 3 belong to the cluster 1, the environmental conditions 4 to 6 belong to the cluster 2, and the environmental conditions 7 to 9 belong to the cluster 3. Further, a new cluster can be defined by further subdividing the cluster or adding a feature of a predetermined dimension. Further, in the example shown in FIG. 5, a new environmental condition 10 is added, and among the environmental conditions 7 to 9 of the cluster 3, the environmental conditions 7 and 8 and the newly added environmental condition 10 create a new cluster. It may be created and tagged with new features, such as "bright environment".

The communication unit 22 is a communication interface that establishes a wired or wireless connection with the agent robot 50. The operation information of the agent robot 50 is acquired from the agent robot 50 via the communication unit 22.

The processing unit 23 executes various types of information processing, and is realized by a processor such as a CPU or GPU and a memory. Specifically, the processing unit 23 has a function of selecting one of the environmental conditions belonging to the cluster based on the operation information of the agent robot 50 and the information specifying the emotion to be caused by the user 5. Have. More specifically, the processing unit 23 selects another environmental condition belonging to the same cluster under a predetermined condition. In addition, the processing unit 23 may change the current environmental condition to another environmental condition in the same cluster when the predetermined condition is satisfied. The predetermined condition means, for example, a state in which a predetermined time has elapsed or a state in which a predetermined reaction is not obtained from the user 5 in the target space S.

The control unit 24 controls the environment generation device 10. Specifically, the control unit 24 extracts an environmental condition for controlling the environment generation device 10 from the storage unit 21 based on the characteristics of the cluster described above, and controls the environment generation device 10 based on this.

The output unit 25 outputs control information for controlling the environment generation device 10 according to an output destination (for example, an input terminal).

(1-3) Operation of Space Control System FIG. 6 is a flowchart for explaining the operation of the space control system 1 according to the present embodiment.

First, the agent robot 50 estimates the emotion that the user 5 wants to cause (S101). The agent robot 50 estimates the emotion that the user 5 intends to cause based on the input information acquired through the above-mentioned input means.

The agent robot 50 selects an emotion to be caused by the user 5 from the estimated emotion of the user 5 based on the sensory stimulus generation model, and starts an action according to the emotion (S102). For example, if the emotion that the user 5 wants to cause is a pleasant emotion, he or she moves the head 502 up and down in accordance with bright music, emits light of bright color, and so on. By continuing such an operation, as shown in FIG. 7A, the interaction between the user 5 and the agent robot 50 can be expected to bring out an affinity between them.

The agent robot 50 transmits the motion information or information specifying the emotion that the user 5 intends to cause (hereinafter, motion information or the like) to the control device 20 (S103). The control device 20 selects the characteristics of the cluster according to the received operation information and the like (S104). For example, it is assumed that the received motion information and the like correspond to the “fun environment”. The control device 20 selects the “fun environment” (cluster 1) from the information shown in FIG. The “environmental condition 1”, the “environmental condition 2”, and the “environmental condition 3” belong to the cluster 1, and one of these environmental conditions is randomly selected by the processing unit 23.

The control device 20 controls the environment generation device 10 according to the selected environmental condition (S105). Specifically, as shown in FIG. 7B, the “image 1” of the environmental conditions 1 to 3 of the “fun environment” selected according to the operation information of the agent robot 50 is a display object drawn with a plurality of circles. R is displayed on the wall W of the target space S, and each display object R moves up and down. This operation is similar to the operation of the agent robot 50. The user 5 can be expected to feel the affinity between the display object R and the agent robot 50 from the previous interaction with the agent robot 50.

After operating for a predetermined time, the agent robot 50 stops the operation started in step S102 (S106). It should be noted that stopping the operation may include stopping all of the above-described operations, or including stopping a part of the movement such as stopping only the head 502. The stop may be a state where it is difficult for the target user 5 to recognize the stop. This makes it possible to reduce the biological characteristics of the agent realized by the agent robot 50. As shown in FIG. 7C, even if the agent robot 50 is stopped, the affinity between the user 5 and the agent robot 50 gives the user 5 an impression that the agent realized by the agent robot 50 controls the environment. You can expect to get it.

As described above, after the user 5 strongly recognizes and stores the existence of the agent realized by the agent robot 50, the biological characteristic of the agent can be reduced by a method such as stopping the operation of the agent robot 50. By this processing, only the operation of the environment generation device 10 can be continued while the user 5 holds the memory of the agent. As a result, for example, it is possible to reduce the annoyance that a highly revealing agent always exists in the environment.

The agent robot 50 obtains a reaction that causes some change in the emotion of the user 5, for example, contact with the agent robot 50 as described above, utterance from the user 5, biometric information, etc. (S107), and there is a change. In the case, or when a predetermined time has elapsed, the process returns to step S101, and the emotion that the user 5 is trying to cause is estimated again.

As described above, the agent robot 50 and the user 5 act bidirectionally so that the agent robot 50 selects the sensory stimulus according to the state and the orientation of the user 5, while the user 5 also needs the sense. You can choose the stimulus.

The agent robot 50 may acquire the reaction of the user 5 even during the operation of step S102 and change the operation pattern when the emotion of the user 5 changes.

In addition, the agent robot 50 is not limited to stopping in step S106, and may be, for example, a slow motion that is continued, a motion that repeats motion and stillness (for example, slow motion), and other operations. A temporary or intermittent stop of the operation may be executed. Similarly, also in step S102, the operation may be such that the operation and the stillness are repeated.

When the memory of the user 5 for the agent realized by the agent robot 50 is weakened, the operation of the agent robot 50 is restarted and the interaction with the user 5 is restarted to reinforce the biological characteristics of the agent itself. May be. How much the user 5 remembers the presence of the agent may be judged from the acceptability and affinity for the user's environmental control estimated from the behavior and the physiological state.

(1-4) Features The spatial control system 1 according to the present embodiment includes the environment generation device 10, the agent robot 50, and the control device 20. The environment generation device 10 can generate one or more environments in the target space S. The agent robot 50 realizes an agent that executes an action according to the emotion that the target user 5 tries to cause. The control device 20 controls the environment generation device 10 so as to generate a predetermined environment according to the operation of the agent robot 50.

An agent realized by a robot or the like can produce an active space such as softening the atmosphere of a place. However, when a person is in contact with such an agent for a long time, the existence of the agent becomes accustomed (becomes tired), and thus it is difficult to maintain the effect for a long time. The space control system 1 according to the present disclosure can represent an effect in which the agent realized by the agent robot 50 makes the user 5 have the impression of controlling the environment. For example, by stopping the operation of the agent robot 50 and executing the operation of erasing the substance of the agent, it is possible to create the presence of the agent to the extent that the habituation does not proceed. With such a function, the active effect of the agent can be maintained for a long time. The atmosphere created by such agents is not always created explicitly, but it is useful for creating an atmosphere in various situations such as conferences, work environments, hospice, restaurants, homes, etc. by maintaining it in the unconscious part of the person. Becomes

(1-5) Modified Example (1-5-1) Modified Example 1
The space control system 1 according to the present disclosure is applicable to, for example, an air conditioning system. In this case, an agent which is recognized by the user 5 through audiovisual sense is provided as an interface of the air conditioner. The interface may be a robot or a character displayed on a voice or a display device. For example, the agent gives an impression that the user 5 has an impression of controlling the environment, and then the user 5 controls the feeling of air. In addition to the role of the air conditioner, which controls the temperature, humidity, airflow, etc. by controlling the air conditioning in this manner, the user 5 is given the sensation that the agent creates the atmosphere in the room. Can be expected.

(1-5-2) Modification 2
In the above description, an arbitrary terminal device having an input device such as a keyboard, a mouse, a touch panel, or a tactile device may be used as the input unit for the agent robot 50 to infer the emotion of the user 5. In this case, the terminal device 30 is connected to the agent robot 50 by wire or wirelessly, and transmits information necessary for estimating the emotion of the user 5 via the communication unit 55. Further, in this case, the user 5 may actively input the emotion he/she wants to be by voice or text. Alternatively, the user 5 may input, by voice or text, what expresses the emotion he/she wants to be, in an onomatopoeia or an onomatopoeia.

Further, the means for estimating the emotion of the user 5 may be provided outside, and the actuator such as the agent robot 50 may acquire the information indicating the emotional state of the user 5 from the same means.

(1-5-3) Modification 3
In the above description, the environment generation device 10 and the control device 20 are separate devices, but they may be integrated into the same device.

(1-5-4) Modification 4
In the above description, the agent is described as an example realized by the anthropomorphic agent robot 50, but the present invention is not limited to this. The agent is realized by actuators such as an air conditioner, a projector, a robot, a color changing device, a rhythm device, a light intensity changing device, a voice device, an odor generating device, and a display device, and realizes biological elements with which humans feel affinity. It only needs to exist. The element constituting the agent may be realized by a device that evokes at least one of the sense of sight, hearing, touch, smell, and taste of the user 5 by its operation.

The actuator does not need to be a device different from the environment generation device 10, and may be a part of the environment generation device 10. Further, the actuator does not have to be a device different from the control device 20, and may be a part of the control device 20 or may include the control device 20.

(2) Creation of Air-Sensing Agent in Space Control System Hereinafter, the significance and function of the agent in the space control system of the present disclosure will be described.

(2-1) Minimal design of agent Minimal design refers to the minimum sensory stimulus necessary to establish the existence of an object in the mind of the user. By presenting only such a minimal stimulus, a blank space is created in which the user can freely imagine the target. By properly incorporating the minimal design that appropriately arouse the imagination of the user into the agent design, it becomes difficult for the user to feel the existence of the designer, and it can be expected that the "brilliance" of the agent can be greatly reduced.

On the other hand, it is extremely difficult for the user to continuously exert a high imagination on the agent and to continue to feel its presence, and at the same time, the production for keeping the user's minimum presence always felt. is necessary. For example, it is known that the human brain shows activity as if there is an agent there, even if there is no sensory input from the actual agent, just by suggesting its existence in the top-down direction. .. It is also known to enhance the presence of intangible agents by making good use of sensory-independent physical properties such as rhythm and concomitant movement. It is also necessary to consider ways to make the presence of agents stable and stable by making full use of these rendering methods.

(2-2) Psychological support based on physical sensation As a method for agents based on minimal design to work on users, it is possible to use physical sensation. It is known that human cognition and emotions are transformed by the presentation of sensory stimuli that are not directly related to it. For example, the quality of decision-making changes depending on the weight of what you have, the visual flow presented to peripheral vision also affects our actions and emotions, and the soft tactile sensation reduces suspicion. Many findings are known that refer to the relationship between physical sensations such as, and cognition and emotions. The process by which physical sensations affect human perception and thinking is called somatic cognition. The inventors do not take advantage of the potential impact of these sensations on cognition and attitudes to provide background psychological support without disturbing the main work users are doing. I thought. Specifically, it is a system design in which agents generate various sensory stimuli to encourage users to perform psychological support.

On the other hand, it is also reported that the reproducibility of such psychological knowledge regarding physical recognition is extremely low. The reason for this is that, although it is very difficult to concentrate bodily sensations into only a single sensation by nature, at present, the laboratory findings in a limited situation conducted in a small number of samples are “verbally”. There are many reports of over-generalization due to "explanation". In order to avoid such over-generalization, we gathered a large amount of data that scrutinized the effects of various multisensory stimuli on our cognition and emotions, from which the senses and cognitions commonly shared by the group were collected. Machine learning the statistical relationship between emotions and emotions. Therefore, it is necessary to extract the generation model of the sensory stimulus that effectively affects cognition and emotion.

(2-3) Formation of interactive loop between user and agent When the psychological support of the user is performed using the generative model that does not depend on the linguistic explanation as described above, how is the generative model adapted to the user's situation? The question arises as to whether or not to select properly. As one of such methods, there is known a system that collects user's behavior/physiological data with various sensors and automatically provides appropriate support for the internal state of the user estimated from the collected data. However, since the human mind is abstract and the individual differences are large, it is extremely difficult to externally guess what kind of support is needed. In addition, such one-way support may increase the psychological reactance of a person and cause a repulsion to the system.

Therefore, we prepare generative models of sensory stimuli with various characteristics in the agent, and while the agent recommends generative model candidates inferred from the personal characteristics of the users who have learned in the past by presenting stimuli, the user also needs It is necessary to design a system with a bidirectional loop structure that takes into account the user's spontaneity, such as selecting the pattern that they are trying to do while working on the agent. This interactive relationship between the user and the system is strengthened especially when the user recognizes the system as an agent rather than a machine. Therefore, making the entire system an agent is also important for smoothly forming such a loop structure. Furthermore, in order to form such a loop structure, it is also important to have a tactile interface that allows the user to intuitively work on the agent by touching or the like.

(2-4) Construction of an ecosystem for sharing agents in a group In order to design a close-in agent as described above, a generation model of sensory stimuli for performing various psychological support is held inside the agent. I need to keep it. In addition, if the number of such generative models is finite, the user may eventually feel "aggression" in the behavior of the agent or become tired of it. Therefore, it is necessary for the agent to successively acquire new generative models. In recent years, attempts have been made to generate new patterns in a program in a self-organizing manner in fields such as artificial life. On the other hand, with such a "machine-dependent" pattern generation method, it is easy to produce patterns similar to existing ones, and it is easy to produce meaningless patterns that are largely different from human sensibilities. It is difficult to stably increase a new generative model.

Therefore, we have prepared a method that allows the user to express the feeling "I want to receive such a sensory stimulus" by creating the sensory stimulus by himself, and always create the sensory stimulus created by the user. It is necessary to save the database shared by the network and design it for use in acquiring a new generative model. However, a system that requires general users with low expertise to create complex sensory stimuli from scratch is not practical. Therefore, after setting a common sensory stimulus protocol as a whole, as a means of creating sensory stimuli, it is possible to create it from a builder application on a full-scale computer that can create sensory stimuli very precisely. A wide variety of types are available, including a simplified GUI on a touch panel that even elderly people can operate, and a tactile interface that can generate sensory stimuli by touching them intuitively. Lower barriers to entry to the limit. By constructing an ecosystem in which various users share agents (generation models) that are close to each other via a network, we try to continuously increase the generation models inside the agents. Ideally, a new sensory stimulus is actually created by the user in the ecosystem without being aware of the user's own creative activity, and it is mechanically absorbed and stored in the database. Shape is desirable. In the design of sharing such agents as a group, by contacting a new type of sensory stimulus created by a stranger through the agent, the creativity that is potentially present in the user is activated, and there is also a seed of new creation. If we can build an ecosystem with a high degree of openness, in which a serendipity chain is created, agents will be able to continuously acquire new generation models.

(2-5) Outline of the proposed "air-sensing agent", which often exceeds the physical characteristics of air, such as "meeting becomes difficult and the air becomes stagnant" or "air is softened by the baby". You may feel the characteristics of air more subjectively in form. Agents often invisible in the air, such as feeling the warmth of being embraced by something big in the sun in the forest, or gaze from the darkness of no one in the cemetery at night. You may feel a sign of. We define our subjective impression of the atmosphere by the word "air feeling", and try to make such an air feeling an agent according to the above-mentioned principle.

Specifically, in addition to an air conditioner, various kinds of sensory stimuli are presented to the entire room to create various feelings of air. We try to implement an air-sensing agent using a robot.

Fig. 8 shows the overall image of the air sensation agent. In addition to physical air temperature, humidity, wind direction and air volume by the air conditioner as sensory stimuli generated by the air sensation agent, the visual, auditory, and olfactory senses presented to the entire room by the projector, speaker, and odor generating device Multisensory stimulation is assumed. It has been reported in previous studies that human perception of air and its metabolic activity are affected by audiovisual stimuli that are not directly related to air. By moving the stimulus presenting device, it becomes possible to generate various air feelings that cannot be produced by the conventional air conditioner. I hope that through such a feeling of atmosphere, it will be possible to provide various types of psychological support by continuing to work on the users in the room in the background. Further, the user can not only passively enjoy the psychological support by the air feeling, but also can create the air feeling desired by the air feeling builder prepared at various levels.

In this system, the air sensation composed of various multi-sensory sensory information is mapped and held in a low-dimensional space described by tactile expression. Compared with other sensations, there are few individual differences in the sense of touch, and by describing a feeling of air that is not actually touched directly on a pseudo-tactile scale, it is possible for multiple users to feel Make it easy to share the feeling of air created by. Then, in this tactile space, various sensory stimuli created and accumulated by the user are clustered, and the agent is made to acquire a minimalistic sensory stimulus generation model for generating an air sensation based on the clustering.

In this system, the air sensation agent not only selects a generative model that statistically creates an air sensation according to the past history, but also "touches" the tactile sensation interface created by combining multiple sensors with various tactile sensations. By doing so, we will build a bidirectional loop structure between the user and the air feeling agent that will spontaneously select the air feeling desired by the user. By forming such a loop structure, even if the agent cannot accurately infer the psychological support desired by the user, it is easy to reach the air feeling desired by the user.

In order to stably establish the bidirectional loop structure between the user and the air feeling agent, the user needs to recognize that the agent is the cause of the air feeling in the field. An aerial robot is prepared to enhance such recognition from the top down. Basically, the air-sensing agent only presents minimal sensory stimuli in the background in order to prevent the user from feeling "vibrancy". By appropriately operating the feeling robot, it continues to keep the user's recognition that it is the agent that creates the air feeling (for example, FIG. 7B). However, if a bidirectional loop structure is sufficiently established between the user and the air-sensing agent, the real robot becomes a factor that causes "vibrancy" to be felt, and the activity is stopped (for example, as shown in Fig. 7C).

(3) Agent Robot Design FIGS. 9A to 9E show an example of the above-described agent robot design. FIG. 9A is a top perspective view of the agent robot. FIG. 9B is a lower perspective view of the agent robot. FIG. 9C is a front view of the agent robot. FIG. 9D is a front view showing a state after the operation of the agent robot (a state in which the head 502 shown in FIG. 2 is retracted). FIG. 9E is a plan view of the agent robot. FIG. 9F is a bottom view of the agent robot.

This device may be internally provided with a computer device, and performs an operation or an output for generating an environment in accordance with a user's emotions in space from an input operation of the user or information obtained based on the user operation. .. When the user touches the head protruding from the center, the head moves down to the position shown in FIG. 9D or moves up again. The head may move up and down continuously.

(4) Other Embodiments The embodiments have been described above, but it will be understood that various changes in form and details can be made without departing from the spirit and scope of the claims.

That is, the present disclosure is not limited to the above embodiments as they are. The present disclosure can be embodied by modifying the constituent elements within the scope not departing from the gist of the present invention at the implementation stage. In addition, the present disclosure can form various disclosures by appropriately combining a plurality of constituent elements disclosed in each of the above-described embodiments. For example, some components may be deleted from all the components shown in the embodiment. Further, the constituent elements may be appropriately combined with different embodiments.

1: space control system 10: environment generation device 20: control device 21: storage unit 22: communication unit 23: processing unit 24: control unit 25: output unit 30: terminal device 50: agent robot 51: control unit 52: detection unit 53: Input part 54: Memory 55: Communication part 56: Output part 57: Power supply 501: Body part 502: Head part 503: Base surface 504: Bottom part R: Display object S: Target space W: Wall

JP, 2003-299013, A

Claims (11)

An environment generation device capable of generating one or more environments in the target space,
An actuator that realizes an agent that performs an action according to the emotion that the target user tries to cause,
A control device for controlling the environment generation device so as to generate a predetermined environment according to the operation of the agent;
And a spatial control system. The actuator is at least one of an air conditioner, a robot, a color changing device, a rhythm device, a light intensity changing device, a voice device, an odor generating device, a projector, and a display device.
The space control system according to claim 1. The agent includes an interface having a biological component,
The space control system according to claim 1. The actuator is capable of implementing the agent to perform multiple actions,
The environment generation device is capable of generating a plurality of environments,
The plurality of operations and the plurality of environments are associated with each other,
The control device controls the environment generation device to generate the predetermined environment based on a correspondence between the plurality of operations and the plurality of environments,
The space control system according to any one of claims 1 to 3. A plurality of the environment generation devices,
The control device controls the plurality of environment generation devices so as to generate a predetermined environment according to the operation of the agent,
The space control system according to claim 1. The control device causes the environment generation device to generate the predetermined environment in synchronization with the operation of the agent, and then temporarily or intermittently stops generation of the environment by the environment generation device, and the actuator is , And temporarily or intermittently stop the operation of the agent,
The space control system according to claim 1. The control device causes the actuator to stop the operation of the agent while causing the environment generation device to generate the predetermined environment in synchronization with the operation of the agent.
The space control system according to claim 1. The environment generation device is a device for stimulating the sense of the user in the target space,
The space control system according to claim 1. The actuator is a device that evokes at least one of the five senses of the user by the action of the agent.
The space control system according to claim 1. The environment generation device is an air conditioner, an acoustic device, a lighting device, an odor generating device, or a projector,
The space control system according to any one of claims 1 to 9. Equipped with an input device that acquires input information,
Based on the input information, the actuator realizes an agent that performs an action according to the emotion that the user is trying to cause,
The input information includes onomatopoeia or onomatopoeia, or information identified based on an event corresponding to the onomatopoeia or onomatopoeia,
The space control system according to claim 1.