Determining device, robot, determining method, and computer program product

Abstract

A determination device includes a processing unit that determines a type of external stimulus accompanying contact with a robot that the robot receives based on first detection data obtained by a sensor that can detect contact with the robot and second detection data obtained by a sound detection unit provided to the robot. A program causes a computer to execute processing that determines a type of external stimulus accompanying contact with a robot that the robot receives based on first detection data obtained by a sensor that can detect contact with the robot and second detection data obtained by a sound detection unit provided to the robot.

Description

Citation of relevant applications

[0001] This application claims priority and interest in Japanese Patent Application No. 2025-076537, filed May 2, 2025. The entire description, claims, and drawings of Japanese Patent Application No. 2025-076537 are referenced in this specification. Technical Field

[0002] This disclosure relates to determination devices, robots, determination methods, and computer program products. Background Technology

[0003] Previously, a robot was known that uses touch sensors to detect external stimuli that accompany contact and performs actions in response to the detected external stimuli, thereby enabling it to act like a living organism (e.g., Japanese Patent Application Publication No. 2003-121274). Summary of the Invention

[0004] The problem that the invention aims to solve However, in the robots of the prior art mentioned above, there is a problem that it is difficult to distinguish and determine external stimuli with different contact methods.

[0005] The purpose of this disclosure is to distinguish and determine external stimuli that are exposed in different ways.

[0006] Methods for solving problems To address the aforementioned issues, the determination device disclosed herein includes a processing unit that determines the type of external stimulus that accompanies contact with the robot based on first detection data and second detection data. The first detection data is data obtained by a sensor capable of detecting contact with the robot, and the second detection data is sound data obtained by a sound detection unit of the robot.

[0007] The effects of the invention According to this disclosure, it is possible to distinguish and determine external stimuli that are contacted in different ways. Attached Figure Description

[0008] Figure 1 This is a diagram showing the appearance of a robot.

[0009] Figure 2 This is a schematic diagram showing the structure of the robot's main body.

[0010] Figure 3 It is a block diagram representing the functional structure of a robot.

[0011] Figure 4 This is a diagram showing the configuration range of touch sensors.

[0012] Figure 5 It is a graph representing the detection data.

[0013] Figure 6 It is a graph representing a standard data table.

[0014] Figure 7 This diagram illustrates the methods for determining "poke" and "touch" in relation to the intensity of contact.

[0015] Figure 8 It is a flowchart showing the control sequence of robot control processing.

[0016] Figure 9 It is a flowchart that represents the control sequence of input decision processing.

[0017] Figure 10 This is a flowchart representing the control sequence for determining and processing external stimuli.

[0018] Figure 11 It is a flowchart that shows the control sequence of the output that determines the processing. Detailed Implementation

[0019] Hereinafter, embodiments of the present disclosure will be described based on the accompanying drawings. Figure 1 As shown, robot 1 comprises a main body 100 and an outer casing 200 covering the entire surface of the main body 100. Robot 1 is a pet robot that mimics small creatures. Robot 1 is capable of performing multiple different actions that mimic the behavior of a creature. The outer casing 200 is made of a soft material and deforms according to the movement of the main body 100. The outer casing 200 may have, for example, fur made of napped fabric and decorative components that mimic eyes. A locking part (not shown) is provided on the back of the outer casing 200 (the side in contact with the main body 100), which can engage with a fastener (not shown) provided on the surface of the main body 100. By engaging the locking part with the fastener, the main body 100 and the outer casing 200 can be prevented from shifting significantly. The number of locking parts and fasteners is kept to a minimum so as not to hinder the movement of the main body 100 and to facilitate the loading and unloading of the outer casing 200. In this embodiment, the locking parts and fasteners are provided at three locations: the left and right eye positions and the rear end of robot 1.

[0020] like Figure 2As shown, the main body 100 of robot 1 has a head 101, a torso 103, and a connecting part 102 connecting the head 101 and the torso 103. The main body 100 has a drive unit 40 for moving the head 101 relative to the torso 103. In robot 1, the head 101 is equivalent to a "movable part". The drive unit 40 has a torsion motor 41 and a vertical movement motor 42. The torsion motor 41 is a servo motor that rotates the head 101 and the connecting part 102 within a predetermined angle range around a first rotation axis 401 extending in the extending direction of the connecting part 102. By the action of the torsion motor 41, the robot 1 achieves the movement of torsion of the head 101. The vertical movement motor 42 is a servo motor that rotates the head 101 within a predetermined angle range around a second rotation axis 402 perpendicular to the first rotation axis 401. By the vertical movement motor 42, the robot 1 achieves the movement of vertical movement of the head 101. The direction of the up-and-down movement of the head 101 can also be tilted relative to the vertical direction depending on the angle of the torsion of the head 101 by the torsion motor 41. By making the torsion motor 41 and / or the up-and-down movement motor 42 move precisely and periodically, the robot 1 can achieve the movement of the head 101 swinging or trembling. By appropriately changing and combining the timing, magnitude, and speed of the movements of the torsion motor 41 and the up-and-down movement motor 42, the robot 1 can perform various actions, such as joyful actions, shocked actions, and breathing actions that simulate biological breathing. Among these, breathing actions are one type of spontaneous action of the robot 1. The main body 100 has a touch sensor 51, a motion sensor 52, an illumination sensor 53, a microphone 54 (sound detection unit), a sound output unit 30, and a power receiving coil 73. The motion sensor 52 includes an accelerometer 521 and a gyroscope sensor 522. The touch sensor 51 is respectively disposed on the upper part of the head 101 and the torso 103. The motion sensor 52 and the power receiving coil 73 are disposed near the lower surface of the torso 103. An illuminance sensor 53 and a sound output unit 30 are located on the upper part of the torso 103. A microphone 54 is located on the upper part near the base of the head 101.

[0021] like Figure 3 As shown, robot 1 includes a CPU 11 (Central Processing Unit) (one or more processing units), RAM 12 (Random Access Memory), storage unit 13, operation unit 20, sound output unit 30, drive unit 40, sensing unit 50, communication unit 60, and power supply unit 70. The CPU 11, RAM 12, and storage unit 13 constitute a determination device 10 for determining the type of external stimulus received by robot 1. All parts of robot 1 are connected via data transmission paths such as buses. Figure 3All the functional structures shown are located in the main body 100. The CPU 11 is a processor that reads and executes the program 131 stored in the storage unit 13 and performs various arithmetic operations, thereby controlling the actions of the robot 1. Furthermore, the robot 1 may have multiple processors (e.g., multiple CPUs), which can also execute multiple processes performed by the CPU 11 in this embodiment. In this case, multiple processors constitute one or more processing units. In this situation, multiple processors can participate in common processing, or multiple processors can independently execute different processes in parallel. The RAM 12 provides memory space for the CPU 11 to operate on, storing temporary data.

[0022] Storage unit 13 is a non-temporary recording medium that can be read by CPU 11, which is a computer, and stores program 131 and various data. Storage unit 13 includes, for example, non-volatile memory such as flash memory. Program 131 is stored in storage unit 13 in the form of computer-readable program code. Data stored in storage unit 13 includes status data 132 and action setting data 133. Status data 132 records data indicating the current state of robot 1 and its surrounding environment. For example, status data 132 records emotional parameters representing simulated emotions of robot 1, personality parameters representing simulated personality of robot 1, data on the number of days robot 1 has grown, the current action pattern of robot 1, sleepiness value representing the intensity of robot 1's sleepiness, and the brightness of the area around robot 1. Status data 132 is updated sequentially according to the history of robot 1's actions. Action setting data 133 sets the reaction actions of robot 1 based on the state of robot 1, the content of external stimuli, etc., as well as the automatic generation actions that robot 1 performs spontaneously without relying on external stimuli. The settings involved in the action content include, for example, the settings for the timing and amount of action of the torsion motor 41 and the up-and-down movement motor 42 of the drive unit 40, and the settings for the pitch, length, and volume of the sound output by the sound output unit 30. Furthermore, the action setting data 133 includes the standard data table 1331 referenced in the external stimulus determination processing described later. The contents of the standard data table 1331 will be described later.

[0023] The operation unit 20 includes operation buttons and operation knobs for power on / off and volume adjustment of the sound output unit 30. The operation unit 20 outputs operation information corresponding to input operations on the operation buttons and operation knobs to the CPU 11. The sound output unit 30 includes a speaker that outputs sound with pitch, length, and volume corresponding to the control signals and sound data sent from the CPU 11. This sound can also be a sound imitating the calls of living organisms. The drive unit 40 operates the aforementioned torsion motor 41 and up / down movement motor 42 according to the control signals sent from the CPU 11.

[0024] The sensing unit 50 includes the aforementioned touch sensor 51, motion sensor 52, illuminance sensor 53, and microphone 54, and outputs the detection data from each sensor and microphone 54 to the CPU 11. The touch sensor 51 and motion sensor 52 constitute sensor S. The touch sensor 51 detects contact between an object and the robot 1. Here, the object can be a user. The touch sensor 51 in this embodiment can also detect the intensity of the contact. The touch sensor 51 may include, for example, a pressure sensor such as an electrostatic capacitance sensor or a piezoelectric sensor, and outputs detection data related to whether or not there is contact with the robot 1 to the CPU 11. The touch sensor 51 detects the intensity of contact with the robot 1 and outputs it to the CPU 11. The touch sensor 51 may also detect pressure above a predetermined first threshold as contact, and not detect pressure below the first threshold. In this case, the first threshold can be changed by the CPU 11. Increasing the first threshold is equivalent to reducing the sensitivity of the touch sensor 51 to contact detection. Figure 2 as well as Figure 4 As shown, touch sensors 51 are respectively disposed on the upper surface of the head 101 of the robot 1, the left side of the upper surface of the torso 103, and the right side of the upper surface of the torso 103. In this embodiment, the head 101 side of the robot 1 is designated as the front, the torso 103 side as the rear, and the direction perpendicular to the front-back direction when viewed from a direction perpendicular to the upper surface of the torso 103 is designated as the left-right direction. The left side of the upper surface of the torso 103 refers to being to the left of the center of the torso 103 in the left-right direction when viewed from a direction perpendicular to the upper surface of the torso 103, and the right side of the upper surface of the torso 103 refers to being to the right of the center of the torso 103 in the left-right direction when viewed from a direction perpendicular to the upper surface of the torso 103. When an object comes into contact with the area where the touch sensors 51 are disposed on the surface of the robot 1, the touch sensors 51 detect contact. On the other hand, when an object comes into contact with a portion of the surface of the robot 1 that is off-range from the area where the touch sensors 51 are disposed (e.g., the portion equivalent to the "neck" between the head 101 and the torso 103), the touch sensors 51 do not detect contact. also, Figure 2 as well as Figure 4The configuration of the touch sensor 51 shown is illustrative, and the configuration range and number of touch sensors 51 can be changed appropriately.

[0025] The motion sensor 52, comprising an accelerometer 521 and a gyroscope 522, detects the motion of the robot 1. The motion of the robot 1 includes movements corresponding to the mechanical forces acting on it. The motion sensor 52 can also be referred to as an inertial sensor. The accelerometer 521 detects the acceleration along each of the three orthogonal axes and outputs the detection data to the CPU 11. The gyroscope 522 detects the angular velocity around each of the three orthogonal axes and outputs the detection data to the CPU 11. Since both the accelerometer 521 and the gyroscope 522 have three detection axes, the motion sensor 52 is also referred to as a six-axis sensor. The illuminance sensor 53 detects the ambient light around the robot 1 and outputs the detection data to the CPU 11. The microphone 54 detects the ambient sound around the robot 1 and outputs the sound detection data to the CPU 11. The microphone 54 can also detect sounds at volumes above a predetermined second threshold as external stimuli and not detect sounds at volumes below the second threshold. In this case, the second threshold can be changed by the CPU 11. Increasing the second threshold is equivalent to decreasing the microphone 54's sensitivity to sound detection.

[0026] The communication unit 60 is a communication module including an antenna, modulation and demodulation circuit, and signal processing circuit, and performs wireless data communication with external devices according to a specified communication standard. The power supply unit 70 includes a battery 71, a balance detection unit 72, and a receiving coil 73. The battery 71 supplies power to various parts of the robot 1. The battery 71 in this embodiment is a rechargeable battery that can be repeatedly charged by contactless charging. The balance detection unit 72 detects the remaining battery level of the battery 71 according to a control signal sent from the CPU 11 and outputs the detection result to the CPU 11. The charging operation of the battery 71 is performed with the robot 1 stored (set) inside a dedicated power supply unit (storage unit, charging base) (not shown). A power supply coil is provided in the power supply unit opposite the receiving coil 73 when the robot 1 is stored. The receiving coil 73 of the robot 1 supplies current to the battery 71 through electromagnetic induction based on the magnetic field generated by the power supply coil. With this structure, the charging operation of the battery 71 automatically starts when the robot 1 is stored in the power supply unit. In addition, the charging method of battery 71 is not limited to non-contact charging, but can also be contact charging.

[0027] Next, the actions of robot 1 will be described. Robot 1, under the control of CPU 11, performs reactive actions and spontaneous actions (automatically generated actions) in response to external stimuli. Based on detection data from touch sensor 51, motion sensor 52, and microphone 54, CPU 11 detects external stimuli received by robot 1 and determines the type of external stimulus. Then, CPU 11 determines the action (reactive action) corresponding to the type of external stimulus received by robot 1, causing robot 1 to perform the determined action. Specifically, CPU 11 drives the torsion motor 41 and the up-and-down movement motor 42 of drive unit 40 in a manner that causes robot 1 to perform the action, and outputs sound from sound output unit 30. Multiple candidate actions for robot 1 to perform when a certain external stimulus is detected are pre-determined for each external stimulus and registered in action setting data 133. CPU 11 determines one action from the multiple actions corresponding to the detected external stimulus according to a predetermined rule, causing robot 1 to perform it. Specifically, the probability of selection for each of the multiple actions corresponding to the external stimulus is pre-determined, and CPU 11 selects and determines an action according to that probability. The candidate actions that can be selected based on a certain external stimulus also vary depending on the robot 1's personality parameters, environmental conditions (ambient brightness), and whether the robot 1 has entered a sleep-mimicking mode at that point in time. Therefore, whenever an external stimulus is detected, multiple actions corresponding to the robot 1's personality and condition are performed. Furthermore, the probability of each of the multiple actions varies depending on the number of days the robot 1 has been growing at that point in time. This results in changes in actions that correspond to the robot 1's growth. In addition to the reaction actions corresponding to the aforementioned external stimuli, the CPU 11 also causes the robot 1 to spontaneously generate actions at predetermined time intervals.

[0028] The following describes a method for determining the type of external stimulus that accompanies contact with robot 1. Hereinafter, the data detected by touch sensor 51, motion sensor 52, and microphone 54 respectively will be denoted as "individual detection data," and the combined individual detection data from touch sensor 51, motion sensor 52, and microphone 54 will be denoted as "detection data D." Figure 5 As shown, the detection data D includes first detection data D1 from sensors S (touch sensor 51 and motion sensor 52) and second detection data D2 from the sound of microphone 54. Figure 5In this document, the individual detection data of touch sensor 51 is abbreviated as "A", the individual detection data of motion sensor 52 is abbreviated as "B", and the individual detection data of microphone 54 is abbreviated as "C". The individual detection data "A" of touch sensor 51 includes, for example, data related to whether or not contact with touch sensor 51 is detected, and the intensity of the detected contact. The individual detection data "B" of motion sensor 52 includes, for example, data on the combined six-axis acceleration and angular velocity of accelerometer sensor 521 and gyroscope sensor 522. The individual detection data "C" of microphone 54 includes, for example, data on the volume of each frequency band of the detected sound and its time-series variation (sound length).

[0029] CPU 11 acquires detection data D from touch sensor 51, motion sensor 52, and microphone 54 at a predetermined frequency. The acquisition frequency of detection data D can be, for example, around several hundred milliseconds. Alternatively, a single detection data D for judgment can be generated by performing predetermined statistical processing on multiple (e.g., three) detection data points. CPU 11 then bases its judgment on this detection data D and... Figure 6 The standard data table 1331 shown determines the type of external stimulus received by robot 1. Standard data table 1331 contains pre-generated standard data Ds corresponding to various external stimuli (multiple specific external stimuli). Standard data Ds are generated based on individual detection data from the touch sensor 51, motion sensor 52, and microphone 54 when robot 1 receives the external stimulus corresponding to the data row. In other words, standard data Ds represents the standard individual detection data detected by the touch sensor 51, motion sensor 52, and microphone 54 when robot 1 receives the external stimulus corresponding to the data row.

[0030] exist Figure 6The standard data table 1331 shown includes external stimuli such as "horizontal body stroking", "hugging and stroking the body", "horizontal head stroking", "hugging and stroking the head", "swaying left and right", "horizontal patting", "hugging and patting", "horizontal poking the body", "hugging and poking the body", "stroking the neck", and "picking up". Each external stimulus is assigned a unique label number. "Horizontal" in these external stimuli indicates the external stimulus received by robot 1 when it is placed on a roughly horizontal surface. "Hugging" indicates the external stimulus received by robot 1 when it is picked up by the user. "Stroking the body" (stroking) indicates that the user strokes the torso 103 of robot 1. "Stroking the head" (stroking) indicates that the user strokes the head 101 of robot 1. "Swaying left and right" indicates that the user picks up robot 1 and rocks it from side to side. "Patting" indicates that the user gently taps robot 1 with their palm or the like. "Patting" is an example of communication when the user wants to soothe robot 1, put it to sleep, or calm it down. Additionally, "patting" is an example of communication reflecting the owner's feelings of "cuteness", "importance", or "desire for calm". "Poke the body" (poking) means the user gently pokes the robot 1 with their fingertips, etc. "Poke the body" is an example of communication when the user wants to play with, tease, or wake the robot 1. Additionally, "poke the body" is an example of communication reflecting the owner's desire to see a reaction, to tease, or to be attended to. "Stroke the neck" means the user strokes the area between the robot 1's head 101 and torso 103. This "stroke the neck" is an external stimulus to an area without a touch sensor 51, therefore the standard data Ds for "stroke the neck" does not include separate detection data "A" corresponding to the touch sensor 51. "Pick up" means the user lifts the robot 1 and hugs it with their arms. Additionally, Figure 6 The external stimuli shown are examples, and the standard data table 1331 may also include standard data Ds corresponding to external stimuli other than these.

[0031] CPU11 export Figure 5 The detection data D shown is... Figure 6The standard data table 1331 shows the similarity of the standard data Ds for each of the multiple external stimuli. Then, the CPU 11 identifies the external stimulus corresponding to the standard data Ds with the highest similarity to the detection data D among the multiple external stimuli in the standard data table 1331 as the external stimulus received by the robot 1. For example, the CPU 11 can also convert the detection data D and the standard data Ds into points in n-dimensional space, where the closer the Euclidean distance between these points, the higher the similarity. For example, a set of averages and deviations can be derived by applying a prescribed process to the three individual detection data contained in the detection data D, and a set of averages and deviations can be derived by applying the same process to the three individual detection data contained in the standard data Ds, and the Euclidean distance between the averages and deviations of the detection data D and the averages and deviations of the standard data Ds can be derived. Here, the deviation can also be a statistical index value (standard deviation, etc.) representing the magnitude of the deviation of the three individual detection data. The averages and deviations of each standard data Ds can also be pre-derived and stored in the storage unit 13. CPU11 can also convert the detection data D and the standard data Ds into vectors in n-dimensional space, and derive the similarity between these vectors (cosine similarity, etc.).

[0032] In this way, by using separate detection data from the microphone 54 in addition to the separate detection data from the touch sensor 51 and the motion sensor 52, it is possible to distinguish and determine external stimuli with different contact methods. This is because, depending on the contact method, the volume, length, etc., of the sound produced by the contact differ, and this difference can be detected by the microphone 54. For example, depending on the contact method, the sound produced by the user's hand contacting the outer casing 200 is different, or the sound produced by the friction between the outer casing 200 and the main body 100 is different. Specifically, a "tap" involves contact with a certain wide area on the surface of the robot 1, thus easily generating a sound caused by the contact between the hand and the outer casing 200 over a wide area. In addition, during a "tap," the outer casing 200 easily moves over a wide area relative to the main body 100 due to the contact, and the sound caused by this movement is easily detected by the microphone 54. On the other hand, "poking" involves contact with a smaller area on the surface of robot 1 than "tapping," making it difficult to generate the sound produced by contact between the hand and the outer casing 200. The movement of the outer casing 200 relative to the main body 100 corresponding to this contact is also easily localized. Therefore, in "poking," the sound is harder to detect by the microphone 54 compared to "stroking" and "tapping." Therefore, even assuming that the individual detection data of the touch sensor 51 and motion sensor 52 are similar among "stroking," "tapping," and "poking," the individual detection data of the microphone 54 are different, allowing for mutual differentiation and detection of "stroking," "tapping," and "poking." Furthermore, "stroking" of robot 1 can be more finely classified and determined. For example, the individual detection data of the microphone 54 differs between "stroking" in a manner that traces along the surface of robot 1 and "stroking" in a manner that grasps the torso 103 from the left and right sides; therefore, according to the method of this embodiment, they can be mutually differentiated and determined. Furthermore, external stimuli such as "touching the neck" can also be detected and determined, even when contact with a part of the body not equipped with touch sensor 51 is involved. For example, in the standard data Ds for "touching the neck," although it does not contain separate detection data of touch sensor 51, it reflects the characteristics of separate detection data of motion sensor 52 and microphone 54 when the external stimulus of "touching the neck" is received. Therefore, even if a certain detection data D does not contain valid separate detection data of touch sensor 51, but contains valid separate detection data of motion sensor 52 and microphone 54, it is possible to determine whether the external stimulus of "touching the neck" has been received based on the similarity between detection data D and standard data Ds for "touching the neck." The above is a typical example of external stimuli that can be distinguished by using microphone 54, but the types of external stimuli that can be determined are certainly not limited to this.

[0033] "Poke" and "touch" can also be distinguished based on the intensity of contact contained in the individual detection data of the touch sensor 51. For example... Figure 7 As shown, if the intensity of contact detected by touch sensor 51 is less than threshold T1, it is determined to be a "poke" on one side (left or right) of the torso 103. If the intensity of contact detected by touch sensor 51 is greater than or equal to threshold T1 but less than threshold T2 (which is greater than threshold T1), it is determined to be a "touch" on one side (left or right) of the torso 103. If the intensity of contact detected by touch sensor 51 is greater than or equal to threshold T2, it is determined to be a "touch" on both sides (left and right) of the torso 103. To enable such determinations, in Figure 6 In the standard data table 1331 shown, multiple standard data Ds can also be registered for a single external stimulus. For example, as the standard data Ds for "horizontal body stroking", standard data Ds corresponding to the following can be prepared in advance: when both sides of the torso 103 are stroked, when the left side is stroked forcefully, and when the right side is stroked forcefully. If the similarity to any of these standard data Ds is high, it is determined to be "horizontal body stroking". Alternatively, for example, based on the intensity of contact in the individual detection data of the touch sensor 51, one of "poking the body" and "stroking the body" can be removed from the external stimuli in the standard data table 1331, and the determination can be made from the remaining external stimuli.

[0034] Next, refer to Figures 8-11 The robot control processing executed by CPU 11 to achieve the aforementioned movements of robot 1 will be described. Robot control processing begins when the power to robot 1 is turned on. For example... Figure 8As shown, when robot control processing begins, CPU 11 executes a prescribed initialization process (step S101) and determines whether robot 1 is in a power-off state (step S102). Here, CPU 11 determines that the robot is in a power-off state if the user has disconnected the power or if the remaining charge of battery 71 is below a predetermined lower limit. If the robot is determined not to be in a power-off state ("No" in step S102), CPU 11 executes the input determination process described later (step S103). Next, CPU 11 executes an output determination process based on the result of the input determination process to determine the output (i.e., action) of robot 1 and causes robot 1 to perform the output (step S104). Afterward, CPU 11 updates the emotion parameters, personality parameters, and growth days in state data 132 according to the history of robot 1's actions and stores them in storage unit 13 (step S105). When step S105 ends, CPU 11 returns the processing to step S102. The loop processing of steps S102 to S105 is executed repeatedly at a predetermined frequency (e.g., several hundred milliseconds). In step S102, if it is determined that the power is off (Yes in step S102), the CPU11 terminates the robot control process.

[0035] like Figure 9 As shown, when the input determination process is invoked, the CPU 11 acquires detection data D, including individual detection data from the touch sensor 51, motion sensor 52, and microphone 54 (step S201). The CPU 11 performs sound recognition processing based on the individual detection data from the microphone 54 (step S202). Here, the CPU 11 obtains sound information related to the detected sound by applying prescribed sound recognition processing to the individual detection data from the microphone 54. This sound information may include, for example, whether it is a human voice or whether it is the voice of a registered user. Next, the CPU 11 executes external stimulus determination processing to determine the external stimuli received by the robot 1 (step S203).

[0036] like Figure 10 As shown, when the external stimulus determination process is invoked, CPU 11 determines whether the cumulative count of the detection data D is "0" (step S301). The cumulative count of the detection data D is... Figure 8 In step S101, it is initialized to "0", and is determined to be "0" when step S301 is initially executed after initialization. If the cumulative count of detected data D is determined to be "0" (yes in step S301), CPU11 determines that it contains... Figure 9The detection data D obtained in step S201 from the individual detection data of touch sensor 51, motion sensor 52, and microphone 54 is determined to be valid (step S302). The conditions for determining validity can be appropriately determined. For example, the individual detection data of touch sensor 51 can be determined to be valid if the contact intensity is above the first threshold. The individual detection data of motion sensor 52 can be determined to be valid if the data of each axis is not an anomaly. The individual detection data of microphone 54 can be determined to be valid if the volume is above the second threshold. The detection data D can also be determined to be valid if the individual detection data of any one of touch sensor 51, motion sensor 52, and microphone 54 is valid. Alternatively, the detection data D can be determined to be valid if two or all of the individual detection data of touch sensor 51, motion sensor 52, and microphone 54 are valid. If the detection data D is determined to be valid ("Yes" in step S303), CPU 11 saves the detection data D in storage unit 13 and increments the accumulated number of detection data D (i.e., adds "1" to the accumulated number). If step S304 ends, or if the detected data D is determined to be invalid ("No" in step S303), CPU11 substitutes "0" into the return value (step S305). A return value of "0" indicates that no external stimulus was detected in the external stimulus determination process.

[0037] If, in step S301, it is determined that the cumulative number of detected data D is 1 or more (No in step S301), CPU11 will... Figure 9The detection data D obtained in step S201 is stored in storage unit 13, and the cumulative number of detection data D is incremented (step S306). CPU 11 determines whether the cumulative number of detection data D is "3" (step S307). If it is determined that the cumulative number is less than "3" ("No" in step S307), CPU 11 transfers the processing to step S305 and substitutes "0" into the return value. If it is determined that the cumulative number is "3" ("Yes" in step S307), CPU 11 generates one detection data D representing the three detection data D stored in storage unit 13 (step S308). For example, CPU 11 can also generate one detection data D by averaging the values ​​of the three detection data D. Alternatively, CPU 11 can also generate one detection data D by selecting and combining the median of the values ​​of the three detection data D. CPU 11 derives the similarity between the detection data D and each of the multiple standard data Ds (step S309). For example, as described above, CPU 11 derives the Euclidean distance between the average and deviation derived from the detection data D and the average and deviation of each standard data Ds. CPU 11 identifies the external stimulus corresponding to the standard data Ds with the highest similarity to the detection data D (e.g., the standard data Ds with the closest Euclidean distance) as the external stimulus received by robot 1 (step S310). CPU 11 substitutes the label number of the external stimulus identified in step S310 into the return value (step S311). If step S311 or S305 ends, CPU 11 terminates the external stimulus determination process and... Figure 9 The input judgment and processing has ended.

[0038] like Figure 11 As shown, when the output decision processing begins, CPU11 is based on Figure 9 The result of the voice recognition processing in step S202, and Figure 10The CPU determines the action to be performed by robot 1 based on the result of the external stimulus determination process (the external stimulus determined by the return value) (step S401). Here, when it is determined that a certain external stimulus has been received, the CPU 11 selects one action from multiple actions pre-established to correspond to that external stimulus, according to the probability assigned to each action. At this time, the CPU 11 can also change the selection of multiple candidate actions based on the robot 1's personality parameters, emotional parameters, ambient illumination, whether it is in sleep mode, and the result of sound recognition processing. Moreover, when it is determined that no external stimulus has been received, i.e., when the return value is "0", the CPU 11 does not determine the action corresponding to the external stimulus. In this case, the CPU 11 can also determine the spontaneous action to be performed by robot 1 if the conditions for spontaneous action execution are met. The CPU 11 determines whether to make robot 1 perform an action (step S402). For example, if robot 1 is performing other actions, the CPU 11 prioritizes those other actions and determines that no new action will be performed (not started). If it is determined that an action should be performed ("Yes" in step S402), the CPU 11 sends a control signal corresponding to the action to the drive unit 40 and the sound output unit 30 (step S403). As a result, the CPU 11 drives the torsion motor 41 and the up-down movement motor 42 of the drive unit 40, and outputs sound from the sound output unit 30 to cause the robot 1 to perform the determined action. If step S403 ends, or if it is determined in step S402 that no action should be performed ("No" in step S402), the CPU 11 terminates the output decision processing.

[0039] As described above, the determination device 10 according to this embodiment includes a CPU 11 as a processing unit. The CPU 11 determines the type of external stimulus accompanying contact with the robot 1 based on first detection data D1 from the sensor S capable of detecting contact with the robot 1 and second detection data D2 from the sound from the microphone 54 of the robot 1. Therefore, in addition to contact with and / or movement of the robot 1, the type of external stimulus can be determined based on the differences in sound generated by contact with the robot 1. Thus, it is possible to distinguish and determine external stimuli with different contact methods. Therefore, it is possible to analyze the communication accompanying the user's contact with the robot 1 in more detail than before.

[0040] Furthermore, sensor S detects at least one of contact with robot 1 and movement of robot 1. Therefore, the type of external stimulus can be determined based on contact with and / or movement of robot 1, and the sound generated by contact with robot 1.

[0041] Furthermore, based on the similarity between the standard data Ds and the first detection data D1 and the second detection data D2, the CPU11 determines which of a plurality of specific external stimuli the external stimulus corresponding to the first detection data D1 and the second detection data D2 is. The standard data Ds is pre-generated data that establishes correspondences with different plurality of specific external stimuli. Thus, by deriving a simple similarity process, the type of external stimulus received by the robot 1 can be determined.

[0042] Furthermore, the standard data Ds corresponding to a specific external stimulus among multiple specific external stimuli is generated based on the detection data from the sensor S and microphone 54 when the robot 1 receives that specific external stimulus. In this way, by using the sensor S and microphone 54, which are used to determine the actual external stimulus, to generate the standard data Ds, the accuracy of the determination of the type of external stimulus can be improved.

[0043] In addition, several specific external stimuli include tapping and stroking of robot 1. Thus, it is possible to distinguish and determine the usual stroking and tapping of robot 1.

[0044] Additionally, sensor S includes at least one of a touch sensor 51 for detecting contact with robot 1 and a motion sensor 52 for detecting movement of robot 1. Thus, it is possible to detect contact with robot 1 and / or movement of robot 1 to determine the type of external stimulus.

[0045] Furthermore, if the first detection data D1 does not contain valid detection data from the touch sensor 51 but does contain valid detection data from the motion sensor 52, the CPU 11 determines the type of external stimulus based on the detection data from the motion sensor 52 included in the first detection data D1 and the second detection data D2. Thus, it is possible to detect external stimuli accompanying contact with an area where the touch sensor 51 is not located and determine its type.

[0046] Furthermore, the robot 1 according to this embodiment includes a determination device 10, a sensor S, and a microphone 54. Therefore, the robot 1 can distinguish and determine external stimuli with different modes of contact. Thus, the robot 1 can analyze in detail the communication accompanying the user's contact with the robot 1 and perform appropriate response actions corresponding to the communication.

[0047] In existing robotics, there is a challenge in distinguishing and determining external stimuli that come into contact with different ways.

[0048] This disclosure enables the differentiation and determination of external stimuli that are contacted in different ways.

[0049] Furthermore, according to this disclosure, the input used to determine the type of external stimulus is organized into first detection data and second detection data, so by appropriately designing the determination process, the increase in the computational load of the processing unit can be suppressed.

[0050] Furthermore, according to this disclosure, the detection information used for determination is specified as information based on the first detection data and the second detection data, thus enabling the type of data required for determination and the management object to be clearly defined, and suppressing the increase in storage resources required for data retention and buffering.

[0051] Furthermore, according to the determination method of this embodiment, by executing the above-described process by the CPU 11, it is possible to distinguish and determine external stimuli with different contact methods. Additionally, the program 131 of this embodiment executes the above-described process by the CPU 11. Thus, it is possible to distinguish and determine external stimuli with different contact methods.

[0052] Furthermore, this disclosure is not limited to the above-described embodiments, and various modifications are possible. For example, the sensor S may only need to have a touch sensor 51, or it may not need to have a motion sensor 52. In this case, the type of external stimulus received by the robot 1 can be determined based on the first detection data D1 of the touch sensor 51 and the second detection data D2 of the microphone 54. In addition, the sensor S may include sensing devices other than the touch sensor 51 and the motion sensor 52.

[0053] Alternatively, CPU11 can also obtain information related to the types of external stimuli received by robot 1 by inputting the detection data D into a prescribed machine learning model, and determine the type of external stimulus based on this information. As a machine learning model, it is possible to use the type of specific external stimulus and the detection data D when robot 1 receives that specific external stimulus as training data to obtain a model.

[0054] Alternatively, the CPU 11 can determine the type of external stimulus received by the robot 1 using methods other than comparing it with standard data Ds for a specific external stimulus in standard data table 1331. For example, the external stimulus can be determined based on the conditions satisfied by converting the detection data D into coordinates in an n-dimensional space through a prescribed process. Alternatively, the external stimulus can be determined based on the magnitude of the determination value by converting the detection data D into a judgment value through a prescribed process. Furthermore, while a method using the three most recent detection data Ds to determine the type of external stimulus has been described, the method is not limited to this; for example, the most recent detection data D can also be used to determine the type of external stimulus.

[0055] Furthermore, the example of robot 1 having the outer casing 200 has been used for illustration, but it is not limited to this; robot 1 may also not have the outer casing 200. In addition, the example of the outer casing 200 covering the entire surface of the main body 100 has been illustrated, but it is not limited to this; the outer casing 200 may also cover the part of the main body 100 in which the touch sensor 51 and the microphone 54 are provided.

[0056] Furthermore, the structure of robot 1 is not limited to Figures 1-4 The illustrated structure could be, for example, a robot that imitates real-world creatures such as humans, animals, birds, and fish; a robot that imitates creatures that do not currently exist, such as dinosaurs; or a robot that imitates fictional creatures.

[0057] Furthermore, while the above description discloses an example of using the flash memory of storage unit 13 as a computer-readable medium for the program involved in this disclosure, it is not limited to this example. Other computer-readable media include information recording media such as HDD (Hard Disk Drive), SSD (Solid State Drive), and CD-ROM. Additionally, a carrier wave is also used in this disclosure as a medium for providing data of the program involved in this disclosure via a communication line.

[0058] Furthermore, the detailed structure and operation of each component of robot 1 in the above embodiments can, of course, be appropriately modified without departing from the spirit of this disclosure. Embodiments of this disclosure have been described, but the scope of this disclosure is not limited to the above embodiments, but includes the scope of the invention as described in the claims and its equivalents.

Claims

1. A determining device, wherein, It has more than one processing unit. The one or more processing units determine the type of external stimulus that accompanies contact with the robot based on the first detection data and the second detection data, wherein the first detection data is data obtained by a sensor capable of detecting contact with the robot, and the second detection data is sound data obtained by a sound detection unit of the robot.

2. The determining device according to claim 1, wherein, The sensor detects at least one of the contact with the robot and the movement of the robot.

3. The determining device according to claim 1 or 2, wherein, The one or more processing units determine, based on the similarity between the standard data and the first detection data and the second detection data, which of a plurality of specific external stimuli the external stimulus corresponding to the first detection data and the second detection data is different from the other two specific external stimuli. The standard data is pre-generated data that corresponds to each of the plurality of specific external stimuli.

4. The determining device according to claim 3, wherein, The standard data corresponding to a specific external stimulus among the plurality of specific external stimuli is data generated based on the detection data obtained by the sensor and the sound detection unit when the robot is subjected to the specific external stimulus.

5. The determining device according to claim 3 or 4, wherein, The specific external stimuli include patting the robot and stroking the robot.

6. The determining device according to any one of claims 1 to 5, wherein, The sensor has at least one of a touch sensor for detecting contact with the robot and a motion sensor for detecting the movement of the robot.

7. The determining device according to any one of claims 1 to 6, wherein, The sensor includes the touch sensor and the motion sensor. When the first detection data does not contain valid detection data from the touch sensor but contains valid detection data from the motion sensor, the processing unit determines the type of the external stimulus based on the detection data from the motion sensor included in the first detection data and the second detection data.

8. A robot, wherein, have: The determining device as described in claim 1; The sensor; and The sound detection unit.

9. A determination method, executed by a computer, wherein, Based on the first detection data and the second detection data, the type of external stimulus that accompanies contact with the robot is determined. The first detection data is data obtained by a sensor capable of detecting contact with the robot, and the second detection data is sound data obtained by a sound detection unit of the robot.

10. A computer program product, wherein, The computer will perform the following processing: Based on the first detection data and the second detection data, the type of external stimulus that accompanies contact with the robot is determined. The first detection data is data obtained by a sensor capable of detecting contact with the robot, and the second detection data is sound data obtained by a sound detection unit of the robot.

Images