Control device

Abstract

To provide a control device capable of enhancing versatility.SOLUTION: A control part 10 controls a machine device provided with driving parts Aa and Ab. The control device 10 includes detection parts Da and Db, processing parts Pa, Pb and Pc, and driving control parts Ca and Cb. The detection parts Da and Db convert a detection signal output from sensors Sa and Sb into sensory information, and transmits the converted sensory information to communication networks Na and Nb. The processing parts Pa, Pb and Pc analyze the sensory information transmitted to the communication networks Na and Nb, generate action command information, and transmit the generated action command information to the communication networks Na and Nb. The driving control parts Ca and Cb analyze the action command information transmitted to the communication networks Na and Nb, and control the driving parts Aa and Ab on the basis of the analyzed action command information.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to a control device.

Background Art

[0002] Conventionally, there is a robot described in Patent Document 1 below. This robot includes a tactile detection unit, a generation unit, a storage unit, an analysis unit, and a control unit. The tactile detection unit detects contact from the outside. The generation unit generates contact information based on the detection result. The storage unit accumulates and stores the contact information for a predetermined period. The analysis unit analyzes the tendency for each user based on the accumulated contact information. The control unit controls a mechanism for causing the robot to take an action and dynamically changes the action based on the analysis result.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the control device described in Patent Document 1, there is room for improvement in terms of versatility.

[0005] The present invention has been made in view of such circumstances, and an object thereof is to provide a control device capable of enhancing versatility.

Means for Solving the Problems

[0006] The control device for solving the above problems is a control device that controls a mechanical device provided with a plurality of drive units, and includes a detection unit, a processing unit, and a drive control unit. The detection unit converts a detection signal output from a sensor for the detection unit into sensory information by detecting predetermined information with the sensor for the detection unit provided in the mechanical device, and transmits the converted sensory information to a transmission path. The processing unit analyzes the sensory information transmitted from the detection unit to the transmission path, generates action command information, which is information on actions to be performed by the mechanical device, based on the analysis result of the sensory information, and transmits the generated action command information to the transmission path. The drive control unit analyzes the action command information transmitted from the processing unit to the transmission path, and controls the drive unit based on the analyzed action command information.

[0007] According to this configuration, since the detection unit, the processing unit, and the drive control unit operate based on sensory information and action command information, it is possible to enhance versatility more than a device that operates with numerical signals or complex control signals such as a conventional control device.

Effect of the Invention

[0008] According to the control device of the present invention, it is possible to enhance versatility.

Brief Description of the Drawings

[0009]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Embodiments for Carrying Out the Invention

[0010] Hereinafter, an embodiment of the control device will be described with reference to the drawings. For ease of understanding of the description, the same reference numerals are given to the same components in each drawing as much as possible, and duplicate descriptions are omitted.

[0011] <First Embodiment> First, the outline of the control device of the first embodiment will be described.

[0012] (Outline of the Control Device) As shown in FIG. 1, the control device 10 of the present embodiment is mounted on a mechanical device 20 that is the object to be controlled. The mechanical device 20 is, for example, a humanoid robot, an industrial robot, or the like. The control device 10 includes a plurality of high-speed detection units Da, a plurality of low-speed detection units Db, a plurality of high-speed drive control units Ca, a plurality of low-speed drive control units Cb, a plurality of upper processing units Pa, a plurality of middle processing units Pb, and a plurality of lower processing units Pc.

[0013] A plurality of high-speed detection units Da, a plurality of high-speed drive control units Ca, a plurality of upper processing units Pa, and a plurality of middle processing units Pb are communicably connected to each other through a high-speed communication network Na. Information transmitted to the high-speed communication network Na is information transmitted in a broadcast manner and is arbitrarily processed by the plurality of high-speed detection units Da, the plurality of high-speed drive control units Ca, the plurality of upper processing units Pa, and the plurality of middle processing units Pb.

[0014] A plurality of low-speed detection units Db, a plurality of low-speed drive control units Cb, a plurality of upper processing units Pa, a plurality of middle processing units Pb, and a plurality of lower processing units Pc are communicably connected to each other via a low-speed communication network Nb. Information transmitted to the low-speed communication network Nb is also information transmitted in a broadcast manner and is arbitrarily processed by the plurality of low-speed detection units Db, the plurality of low-speed drive control units Cb, the plurality of upper processing units Pa, the plurality of middle processing units Pb, and the plurality of lower processing units Pc.

[0015] The high-speed detection unit Da and the low-speed detection unit Db are parts that detect a predetermined physical quantity in the mechanical device 20. For this purpose, the high-speed detection unit Da and the low-speed detection unit Db each have sensors Sa and Sb for detecting the predetermined physical quantity. The sensors Sa and Sb are mounted on the mechanical device 20 and are, for example, camera sensors, video sensors, acoustic sensors, attitude sensors, taste sensors, radio sensors, gas sensors, temperature sensors, contact sensors, and pressure sensors. The sensor Sa mounted on the high-speed detection unit Da is required to operate faster than the sensor Sb mounted on the low-speed detection unit Db. Whether various sensors are classified into the high-speed detection unit Da or the low-speed detection unit Db depends on the configuration of the mechanical device 20 that is the control target of the control device 10. For example, when the mechanical device 20 is a humanoid robot, there may be mounted a camera sensor for acquiring surrounding information, a contact sensor for detecting whether any object has come into contact with the robot, and the like. In this case, since the image information captured by the camera sensor is used to control the entire robot, it is desirable that the image information be processed at a higher speed. Therefore, the camera sensor is classified as one of the sensors Sa of the plurality of high-speed detection units Da. On the other hand, regarding the contact information detected by the contact sensor, it is rarely used as highly urgent information when controlling the robot. Therefore, the contact sensor is classified as one of the sensors Sb of the plurality of low-speed detection units Db.

[0016] The detection units Da and Db convert the detection signals output from the sensors Sa and Sb into sensory information by detecting a predetermined physical quantity with the sensors Sa and Sb, abstract the converted sensory information, and transmit it to the high-speed communication network Na. For example, when the sensor Sb is a contact sensor and the sensor Sb is provided on the right hand of the robot, the low-speed detection unit Db generates verbalized sensory information such as "The right hand of the robot is touching a hard object." or "The right hand of the robot is touching a cold object." based on the detection signal of the sensor Sb. In this embodiment, the process of verbalizing sensory information corresponds to the process of abstracting sensory information. Then, the low-speed detection unit Db transmits the verbalized sensory information to the low-speed communication network Nb. Note that the sensory information includes information representing the five human senses and information on the position where the sensation was obtained. When a detection signal is output from the sensor Sa by detecting a predetermined physical quantity, the high-speed detection unit Da also transmits sensory information corresponding to the detection signal to the high-speed communication network Na.

[0017] The sensory information transmitted from the high-speed detection unit Da to the high-speed communication network Na is acquired by a plurality of upper processing units Pa and a plurality of middle processing units Pb, respectively. Also, the sensory information transmitted from the low-speed detection unit Db to the low-speed communication network Nb is acquired by a plurality of upper processing units Pa, a plurality of middle processing units Pb, and a plurality of lower processing units Pc, respectively. Each of the processing units Pa, Pb, and Pc analyzes the sensory information acquired via the communication networks Na and Nb, and generates action command information, which is information on the actions to be performed by the mechanical device 20, based on the analysis results. The action command information includes information defining the actions of the entire mechanical device 20 and information defining the operations of each part of the mechanical device 20.

[0018] The upper processing unit Pa, the middle processing unit Pb, and the lower processing unit Pc have different processing contents. For example, when the mechanical device 20 that is the control target of the control device 10 is a humanoid robot, the upper processing unit Pa generates action command information that determines the actions to be taken by the entire robot, such as the direction in which the mechanical device 20 should move. The middle processing unit Pb and the lower processing unit Pc generate action command information that determines the actions of each of the plurality of parts of the robot. For example, the plurality of middle processing units Pb generate action command information that determines the actions of each of the plurality of hands of the robot. Also, the plurality of lower processing units Pc generate motion command information that determines the actions of each of the plurality of arms of the robot. The processing of the middle processing unit Pb is prioritized over the processing of the lower processing unit Pc. Also, the processing of the upper processing unit Pa is prioritized over the respective processing of the lower processing unit Pc and the middle processing unit Pb. One of the plurality of upper processing units Pa, the plurality of middle processing units Pb, and the plurality of lower processing units Pc can exchange various information with an external device De such as a random number generator.

[0019] For example, when the low-speed detection unit Db transmits sensory information such as "The right hand of the robot is touching a cold object." to the low-speed communication network Nb and the sensory information is received by the middle processing unit Pb, the middle processing unit Pb analyzes the sensory information and generates action command information such as "Immediately move the right hand of the robot away from the object." Then, the middle processing unit Pb transmits the generated action command information to the high-speed communication network Na and the low-speed communication network Nb. The other upper processing unit Pa and the lower processing unit Pc also operate in the same manner based on the sensory information transmitted from the detection units Da and Db to the high-speed communication network Na and the low-speed communication network Nb.

[0020] The action command information transmitted from the upper processing unit Pa and the middle processing unit Pb to the high-speed communication network Na is received by a plurality of high-speed drive control units Ca. Also, the action command information transmitted from the upper processing unit Pa, the middle processing unit Pb, and the lower processing unit Pc to the low-speed communication network Nb is received by a plurality of low-speed drive control units Cb. The high-speed drive control unit Ca controls the high-speed drive unit Aa provided in the mechanical device 20. The low-speed drive control unit Cb controls the low-speed drive unit Ab provided in the mechanical device 20. The drive units Aa and Ab are a motor device, a speaker device, a lighting device, etc. that constitute the mechanical device 20. The high-speed drive unit Aa is a device that requires a faster operation than the low-speed drive unit Ab. Whether the various devices provided in the mechanical device 20 are classified into the high-speed drive unit Aa or the low-speed drive unit Ab depends on the configuration of the mechanical device 20 that is the control target of the mechanical device 20. For example, when the mechanical device 20 is a humanoid robot, the actuator device that moves the hand of the robot is classified into the high-speed drive unit Aa because a high-speed operation is required. Also, the actuator device that moves the arm of the robot is classified into the low-speed drive unit Ab because a very high-speed operation is not required.

[0021] The drive control units Ca and Cb control the drive units Aa and Ab that are the control targets based on the action command information transmitted from the processing units Pa, Pb, and Pc to the communication networks Na and Nb. For example, when the middle processing unit Pb transmits action command information such as "Immediately move the right hand of the robot away from the object." to the high-speed communication network Na and that action command information is received by the high-speed drive control unit Ca, the high-speed drive control unit Ca analyzes the action command information and operates the high-speed drive unit Aa, which is the actuator device that moves the hand of the robot.

[0022] (Specific Configuration of Mechanical Device and Control Device) Next, the specific configuration of the control device 10 when the mechanical device 20 shown in FIG. 1 is a humanoid robot device will be described.

[0023] As shown in FIG. 2, the robot device 30 of the present embodiment includes a body 31, a head 32, shoulders 33a and 33b, arms 34a and 34b, hands 35a and 35b, a waist 36, and legs 37a and 37b. The robot device 30 is driven by the power of a battery 38 built into the waist 36.

[0024] The head 32 is provided with a camera sensor 40, a distance measuring sensor 41, a voice sensor 42, and a speaker device 43. The camera sensor 40 images the front of the robot and acquires image data of the front of the robot. The distance measuring sensor 41 is a sensor that measures the distance to an object existing in front of the robot. The voice sensor 42 is a sensor that detects sounds around the robot. The speaker device 43 has a function as the mouth of the robot and emits voices, music, etc.

[0025] Actuator devices 330a and 330b are respectively built into the shoulders 33a and 33b. The actuator devices 330a and 330b operate the arms 34a and 34b respectively. In the present embodiment, the actuator devices 330a and 330b correspond to the drive units.

[0026] Contact sensors 50 to 53 are respectively provided on the arms 34a and 34b. Also, contact sensors 54 and 55 are respectively provided on the hands 35a and 35b. Further, contact sensors 56 to 59 are respectively provided on the legs 37a and 37b. The contact sensors 50 to 59 are sensors capable of detecting whether or not an object has come into contact. Also, the contact sensors 50 to 59 are capable of detecting physical properties of the contacted object, such as elastic properties and viscous properties, and output a detection signal according to the detected physical properties.

[0027] Actuator devices 350a and 350b are respectively built into the hands 35a and 35b. The actuator devices 350a and 350b operate the hands 35a and 35b respectively.

[0028] Next, with reference to FIGS. 3 and 4, a specific configuration of the control device 10 mounted on the robot device 30 will be described.

[0029] The control device 10 includes a high-speed communication network Na as shown in FIG. 3 and a low-speed communication network Nb as shown in FIG. 4.

[0030] As shown in FIG. 3, a high-speed detection units Da1 to Da5, high-speed drive control units Ca1 to Ca3, upper-level processing units Pa1 to Pa3, and middle-level processing units Pb1, Pb2 are connected to the high-speed communication network Na.

[0031] The high-speed detection units Da1 to Da5 are parts that process the detection signals of the camera sensor 40, the distance measurement sensor 41, the voice sensor 42, and the contact sensors 54, 55 respectively. The high-speed drive control units Ca1 to Ca3 are parts that control the speaker device 43 and the actuator devices 350a, 350b respectively.

[0032] Based on the image information acquired by the camera sensor 40, the high-speed detection unit Da1 generates sensory information related to the vision of the robot device 30 and transmits the generated sensory information to the high-speed communication network Na. The sensory information related to vision is, for example, information such as "The signal existing in front of the robot's eyes is a red signal."

[0033] Based on the information on the distance to a predetermined object acquired by the distance measurement sensor 41, the high-speed detection unit Da2 generates sensory information related to the vision of the robot device 30 and transmits the generated sensory information to the high-speed communication network Na. The sensory information related to vision is, for example, information such as "There is an obstacle 5 meters ahead of the robot."

[0034] The high-speed detection unit Da3 generates sensory information related to the robot's hearing based on the audio information acquired by the audio sensor 42, and transmits the generated sensory information to the high-speed communication network Na. The sensory information related to hearing is information such as "The sound of a train can be heard.", for example.

[0035] The high-speed detection units Da4 and Da5 generate sensory information related to the tactile sense of the robot device 30 based on the contact information acquired by the contact sensors 54 and 55, and transmit the generated sensory information to the high-speed communication network Na. The sensory information related to the tactile sense is information such as "The right hand of the robot is in contact with a hard object.", for example.

[0036] The upper-level processing units Pa1 to Pa3 generate action command information based on the sensory information transmitted from the high-speed detection units Da1 to Da5 to the high-speed communication network Na, respectively, and transmit the generated action command information to the high-speed communication network Na. For example, the upper-level processing unit Pa1 generates action command information that determines the actions of the entire robot device 30 by using the sensory information transmitted from the high-speed detection units Da1 to Da5. The upper-level processing unit Pa2 also generates action command information that determines the actions of the entire robot device 30 by using the sensory information transmitted from the high-speed detection units Da1 to Da5. The upper-level processing unit Pa1 generates action command information related to the actions of a larger robot device 30 than the upper-level processing unit Pa2. Since the upper-level processing unit Pa1 is located higher than the upper-level processing unit Pa2, the action command information of the upper-level processing unit Pa1 takes precedence over the action command information of the upper-level processing unit Pa2. The upper-level processing unit Pa3 generates action command information related to, for example, audio by using the sensory information transmitted from the high-speed detection units Da1 to Da5.

[0037] The right-hand middle processing unit Pb1 generates action command information that determines the actions of the right hand part 35a of the robot device 30 by using the sensory information transmitted from the high-speed detection units Da1 to Da5, and transmits the generated action command information to the high-speed communication network Na. The left-hand middle processing unit Pb2 generates action command information that determines the actions of the left hand part 35b of the robot device 30 by using the sensory information transmitted from the high-speed detection units Da1 to Da5, and transmits the generated action command information to the high-speed communication network Na.

[0038] The high-speed drive control unit Ca1 controls the speaker device 43 based on the action command information related to sound among the action command information transmitted from the processing units Pa1 to Pa3, Pb1, and Pb2 to the high-speed communication network Na.

[0039] The high-speed drive control unit Ca2 controls the actuator device 350a of the right hand part 35a based on the action command information related to the right hand among the action command information transmitted from the processing units Pa1 to Pa3, Pb1, and Pb2 to the high-speed communication network Na.

[0040] The high-speed drive control unit Ca3 controls the actuator device 350b of the left hand part 35b based on the action command information related to the left hand among the action command information transmitted from the processing units Pa1 to Pa3, Pb1, and Pb2 to the high-speed communication network Na.

[0041] As shown in FIG. 4, the low-speed communication network Nb is connected to the low-speed detection units Db1 to Db8, the low-speed drive control units Cb1 and Cb2, and the lower processing units Pc1 to Pc3.

[0042] The low-speed detection units Db1 to Db8 generate sensory information related to the tactile sensation of the robot device 30 based on the contact information acquired by the contact sensors 50 to 53, 56 to 59, and transmit the generated sensory information to the high-speed communication network Na. The sensory information related to the tactile sensation is information such as "the right foot of the robot is in contact with a soft object.", for example.

[0043] The lower-level processing units Pc1 to Pc3 generate action command information that determines the actions of the arm parts 34a and 34b of the robot device 30 based on the sensory information transmitted from the contact sensors 50 to 53, 56 to 59, and transmit the generated action command information to the low-speed communication network Nb.

[0044] The low-speed drive control units Cb1 and Cb2 control the actuator devices 330a and 330b provided on the shoulders 33a and 33b respectively based on the action command information related to the arm parts 34a and 34b among the action command information transmitted from the lower-level processing units Pc1 to Pc3 to the low-speed communication network Nb.

[0045] (Configuration of the detection unit) Next, the configurations of the detection units Da1 to Da5 and Db1 to Db8 will be specifically described. Since each of the detection units Da1 to Da5 and Db1 to Db8 has the same or similar configuration, hereinafter, the configuration of the high-speed detection unit Da4 corresponding to the contact sensor 54 of the right hand part 35a will be described as a representative.

[0046] As shown in FIG. 5, the high-speed detection unit Da4 includes a preprocessing unit 70, a recognition unit 71, a learning unit 72, an estimation unit 73, a determination unit 74, an imparting unit 75, a verbalization processing unit 76, a data output unit 77, a communication processing unit 78, a data reception unit 79, a writing processing unit 80, a data compression unit 81, and a memory controller 82. The recognition unit 71, the learning unit 72, the estimation unit 73, the memory controller 82, and the verbalization processing unit 76 are communicably connected to each other via a data / memory bus 83.

[0047] The preprocessing unit 70 performs preprocessing on the detection signal output from the contact sensor 54. The preprocessing is filtering processing or the like.

[0048] The recognition unit 71 recognizes the contact information detected by the contact sensor 54 by analyzing the detection signal of the contact sensor 54 that has been preprocessed by the preprocessing unit 70. The recognition unit 71 is composed of a neural network NN as shown in FIG. 6. As shown in FIG. 6, the neural network NN includes a plurality of input layers 1000, a plurality of intermediate layers 1001, and a plurality of output layers 1002. The detection signal of the contact sensor 54 that has been preprocessed is input to the input layer 1000. The intermediate layer 1001 acquires information from the input layer 1000 and performs various operations based on the acquired information. The output layer 1002 outputs a plurality of pieces of data that have been processed by an activation function by multiplying predetermined weights in the input layer 1000 and the intermediate layer 1001. The output layer 1002 of the recognition unit 71 outputs the object information detected by the contact sensor 54. This detected object information includes, for example, respective numerical data such as hardness, elastic characteristics, and viscosity.

[0049] The learning unit 72 sequentially learns the correspondence between the detection signal of the contact sensor 54 that has been preprocessed by the preprocessing unit 70 and the object information detected by the contact sensor 54. The learning unit 72 acquires the object information detected by the contact sensor 54 from the determination unit 74. The learning unit 72 is composed of a neural network NN as shown in FIG. 6. The learning unit 72 outputs estimated object information by using the detection signal of the contact sensor 54 that has been preprocessed by the preprocessing unit 70 as input information and using learning information.

[0050] The estimation unit 73 outputs estimated object information by using the detection signal of the contact sensor 54 that has been preprocessed by the preprocessing unit 70 as input information and using machine learning, a computer, or the like.

[0051] The determination unit 74 calculates the final detected object property information by synthesizing the detected object property information output from the recognition unit 71 and the estimated object property information output from the learning unit 72 and the estimation unit 73 respectively, using a weighting coefficient or the like. Note that the determination unit 74 transmits the calculated final detected object property information to the learning unit 72. The learning unit 72 executes a learning process based on the final detected object property information transmitted from the determination unit 74 and the detection signal of the contact sensor 54 when the object property information is detected.

[0052] The imparting unit 75 generates sensory information corresponding to the object property information from the final detected object property information output from the determination unit 74. Specifically, as shown in FIG. 7, a meaning library 821 is stored in a storage device 820 controlled by a memory controller 82. The meaning library 821 stores information indicating the correspondence between a plurality of object property information and a plurality of sensory information as shown in FIG. 8, for example. The imparting unit 75 identifies the object property information closest to the current detected object property information from among the plurality of object property information shown in FIG. 8 based on the final detected object property information output from the determination unit 74, and outputs the sensory information corresponding to the identified object property information. In this way, the imparting unit 75 corresponds to a part that imparts human sensory information to the final detected object property information output from the determination unit 74.

[0053] The verbalization processing unit 76 converts the sensory information transmitted from the imparting unit 75 into a data format that can be transmitted to the high-speed communication network Na. The verbalization processing unit 76 is composed of a neural network NN as shown in FIG. 6. When sensory information such as "slimy" is transmitted from the imparting unit 75, the verbalization processing unit 76 generates sensory information such as "The right hand of the robot is in contact with a slimy object." so that the position where the physical property is detected can be specified. The sensory information generated by the verbalization processing unit 76 is transmitted to the high-speed communication network Na via the data output unit 77 and the communication processing unit 78. In the present embodiment, the verbalization processing unit 76 is an example of an abstraction unit for a detection unit that abstracts sensory information.

[0054] The data compression unit 81 compresses the data of the detection signal of the contact sensor 54 that has been preprocessed by the preprocessing unit 70. The compressed data of the detection signal of the contact sensor 54 compressed by the data compression unit 81 is transmitted to the high-speed communication network Na via the data output unit 77 and the communication processing unit 78.

[0055] The communication processing unit 78 performs the process of transmitting the data transmitted from the data output unit 77 to the high-speed communication network Na, and receives various types of information transmitted on the high-speed communication network Na. The various types of information transmitted on the high-speed communication network Na are information transmitted from other high-speed detection units Da1 to Da3, Da5, high-speed drive control units Ca1 to Ca3, upper processing units Pa1 to Pa3, and middle processing units Pb1, Pb2 connected to the high-speed communication network Na. The information received by the communication processing unit 78 is transmitted to the memory controller 82 via the data reception unit 79 and the writing processing unit 80.

[0056] The memory controller 82 controls the storage device 820 shown in FIG. 7. In the storage device 820, in addition to the meaning library 821, feature data 822, related data 823, parameters 824, label data 825, original data 826, etc. are stored. The memory controller 82 updates various types of data stored in the storage device 820 based on, for example, the data transmitted from the writing processing unit 80. Also, various types of data stored in the storage device 820 are used by the determination unit 74 and the like.

[0057] (Configuration of the processing unit) Next, the configurations of the processing units Pa1 to Pa3, Pb1, Pb2, Pc1 to Pc3 will be described. Since the processing units Pa1 to Pa3, Pb1, Pb2, Pc1 to Pc3 have the same or similar configurations, hereinafter, the configuration of the right-hand middle processing unit Pb1 that controls the right-hand part 35a will be described as a representative.

[0058] As shown in FIG. 9, the right-hand middle processing unit Pb1 includes an external I / F (interface) 90, a preprocessing unit 91, a recognition unit 92, a learning unit 93, other processing unit 94, an estimation unit 95, a determination unit 96, an imparting unit 97, a verbalization processing unit 98, a data output unit 99, a communication processing unit 100, a data reception unit 101, a writing processing unit 102, a data compression unit 103, a memory controller 104, an analysis unit 105, an action planning unit 106, and a self-recognition unit 107. The recognition unit 92, the learning unit 93, the other processing unit 94, the estimation unit 95, the verbalization processing unit 98, the memory controller 104, the action planning unit 106, and the self-recognition unit 107 are communicably connected to each other via a data / memory bus 140. Among the elements shown in FIG. 9, elements having the same names as those of the elements shown in FIG. 5 perform similar operations. Therefore, the following description will focus on the differences.

[0059] The external I / F 90 is a part to which an external device De different from the robot device 30 can be connected, and acquires information transmitted from the external device De. The external device De is, for example, a unique random number generator. The information acquired by the external I / F 90 is transmitted to the recognition unit 92, the learning unit 93, the other processing unit 94, and the estimation unit 95 via the preprocessing unit 91, respectively. The other processing unit 94 is a part that performs processing different from the processing performed by the recognition unit 92, the learning unit 93, and the estimation unit 95 on the transmission information of the external device De that has been preprocessed by the preprocessing unit 91.

[0060] In the right - hand intermediate - processing unit Pb1, for example, when the sensory information transmitted from the high - speed detection unit Da4 to the high - speed communication network Na is received by the communication processing unit 100, the sensory information is input to the language - processing unit 98 via the communication processing unit 100 and the data reception unit 101. After being converted into a data format analyzable by the analysis unit 105, it is input to the analysis unit 105. At this time, if the sensory information is, for example, information such as "The right hand of the robot is in contact with a slimy object.", the analysis unit 105 extracts object information from the information. The extracted object information includes information on the position where the sensation is detected and object information indicating the sensory information. The object information indicating the sensory information includes numerical data such as hardness, elastic characteristics, and viscosity. The analysis unit 105 transmits the extracted object information to the memory controller 104 as an analysis result.

[0061] The action - planning unit 106 obtains the analysis result of the analysis unit 105 via the memory controller 104 and the determination unit 96. The action - planning unit 106 is composed of a neural network NN as shown in FIG. 6. The action - planning unit 106 generates recommended action information for the right - hand part 35a using the analysis result of the analysis unit 105 as input information. The recommended action information includes the moving distance, moving direction, moving speed, etc. of the right - hand part 35a. The recommended action information of the right - hand part 35a generated by the action - planning unit 106 is input to the determination unit 96.

[0062] The self - recognition unit 107 obtains the analysis result of the analysis unit 105 via the memory controller 104 and the determination unit 96. The self - recognition unit 107 is composed of a neural network NN as shown in FIG. 6. The self - recognition unit 107 generates recognition information indicating the current situation where the right - hand part 35a is placed using the analysis result of the analysis unit 105 as input information. The recognition information includes information on whether any object is in contact with the right - hand part 35a and information on the distance from the right - hand part 35a to any object. The recognition information of the right - hand part 35a generated by the self - recognition unit 107 is input to the determination unit 96.

[0063] The determination unit 96 generates the final motion information of the right hand part 35a based on the recommended motion information of the right hand part 35a generated by the action planning unit 106 and the recognition information of the right hand part 35a generated by the self - recognition unit 107. For example, when the determination unit 96 determines based on the recognition information of the right hand part 35a that the right hand part 35a is in contact with some object, it incrementally corrects the value of the moving speed included in the recommended motion information of the right hand part 35a, and transmits the recommended motion information with the correction reflected to the granting unit 97 as the final recommended motion information.

[0064] The granting unit 97 generates the action command information that the right hand part 35a should perform from the final recommended motion information of the right hand part 35a output from the determination unit 96. Specifically, in the storage device controlled by the memory controller 104, a semantic library 1040 showing the correspondence between a plurality of motion information and a plurality of action command information as shown in FIG. 10, for example, is stored. The granting unit 97 identifies the motion information closest to the current recommended motion information from among the plurality of motion information shown in FIG. 10 based on the final motion information of the right hand part 35a output from the determination unit 96, and outputs the action command information corresponding to the identified motion information.

[0065] The language - conversion processing unit 98 converts the action command information transmitted from the granting unit 97 into a format for transmission on the high - speed communication network Na. The language - conversion processing unit 98 is composed of a neural network NN as shown in FIG. 6. When action command information such as "move the right hand part 35a upward at a speed of ●●" is transmitted from the granting unit 97, the language - conversion processing unit 98 generates action command information such as "Immediately move the robot's right hand upward." The action command information generated by the language - conversion processing unit 98 is transmitted to the high - speed communication network Na via the data output unit 99 and the communication processing unit 100. In this embodiment, the language - conversion processing unit 98 is an example of an abstraction unit for an abstraction processing unit that abstracts action command information.

[0066] (Configuration of the drive control unit) Next, the configurations of the drive control units Ca1 to Ca3, Cb1, and Cb2 will be specifically described. Since the drive control units Ca1 to Ca3, Cb1, and Cb2 have the same or similar configurations, the configuration of the high-speed drive control unit Ca2 that controls the actuator device 350a of the right hand part 35a will be representatively described below.

[0067] As shown in FIG. 11, the high-speed drive control unit Ca2 includes a preprocessing unit 110, a recognition unit 111, a learning unit 112, an estimation unit 113, a determination unit 114, an assignment unit 115, a verbalization processing unit 116, a data output unit 117, a communication processing unit 118, a data reception unit 119, a writing processing unit 120, a data compression unit 121, a memory controller 122, an analysis unit 123, a control unit 124, a driver 125, and a sensor 126. The recognition unit 111, the learning unit 112, the estimation unit 113, the memory controller 122, and the verbalization processing unit 116 are communicably connected to each other via a data / memory bus 128. Among the elements shown in FIG. 11, since the elements having the same names as the elements shown in FIG. 5 perform similar operations, the following description will focus on the differences.

[0068] In the high-speed drive control unit Ca2, for example, when the action command information transmitted from the right hand middle position processing unit Pb1 to the high-speed side communication network Na is received by the communication processing unit 118, the action command information is input to the verbalization processing unit 116 via the communication processing unit 118 and the data reception unit 119, and after being converted into a data format processable by the analysis unit 123, it is input to the analysis unit 123. At this time, when the action command information is information such as "Immediately move the right hand of the robot upward.", the analysis unit 123 generates a control signal for the actuator device 350a from the information. Specifically, the analysis unit 123 sets the driving amount, driving direction, etc. of the actuator device 350a necessary to immediately move the right hand part 35a of the robot device 30 upward, and then transmits a control signal corresponding to the set driving amount and driving direction to the control unit 124.

[0069] The control unit 124 controls the actuator device 350a via the driver 125 based on the control signal transmitted from the analysis unit 123. Thereby, the operation according to the action command information is realized by the actuator device 350a.

[0070] The sensor 126 detects the operating state of the right hand part 35a of the robot device 30 and outputs a detection signal corresponding to the detected operating state. In the present embodiment, the right hand part 35a corresponds to the object to be processed. Note that the sensor 126 may detect the operating state of the actuator device 350a. The detection signal of the sensor 126 is input to the recognition unit 111, the learning unit 112, and the estimation unit 113 through the preprocessing unit 110, whereby the operation result information corresponding to the detection signal of the sensor 126 is generated by the addition unit 115. This operation result information is transmitted to the high-speed side communication network Na via the language conversion processing unit 116, the data output unit 117, and the communication processing unit 118. In the present embodiment, the language conversion processing unit 116 is an example of an abstraction unit for the drive unit that abstracts the operation result information.

[0071] The operation result information transmitted to the high-speed side communication network Na by the high-speed drive control unit Ca2 of the right hand part 35a is received by the communication processing unit 100 shown in FIG. 9, for example, and input to the analysis unit 105 via the data reception unit 101 and the language conversion processing unit 98, and the object information is extracted by the analysis unit 105. The object information extracted by the analysis unit 105 is input to the action planning unit 106 via the memory controller 104 and the determination unit 114. Thereby, the action planning unit 106 can analyze whether or not the right hand part 35a of the robot device 30 is operating appropriately based on this object information and based on the action command information transmitted by itself. Further, when the right hand part 35a of the robot device 30 is not operating appropriately, the action planning unit 106 generates more appropriate recommended operation information for the right hand part 35a and outputs the generated recommended operation information to the determination unit 96. Thereby, the right hand part 35a of the robot device 30 operates more appropriately. In other words, the feedback control of the right hand part 35a of the robot device 30 is realized.

[0072] (Operations and Effects of Control Device 10 of the Present Embodiment) As described above, the control device 10 of the present embodiment controls a robot device 30 (mechanical device) provided with a speaker device 43 and actuator devices 330a, 330b, 350a, and 350b. In the present embodiment, the speaker device 43 and the actuator devices 330a, 330b, 350a, and 350b correspond to a plurality of drive units. The control device 10 includes detection units Da1 to Da5, Db1 to Db8, processing units Pa1 to Pa3, Pb1, Pb2, Pc1 to Pc3, and drive control units Ca1 to Ca3, Cb1, Cb2. The detection units Da1 to Da5, Db1 to Db8 convert detection signals output from the sensors 40 to 42, 50 to 59 (sensors for detection units) into sensory information by detecting predetermined information by each of the sensors 40 to 42, 50 to 59 provided in the robot device 30, and verbalize (abstract) the converted sensory information and transmit it to communication networks Na, Nb (transmission paths). The processing units Pa1 to Pa3, Pb1, Pb2, Pc1 to Pc3 analyze the sensory information transmitted from the detection units Da1 to Da5, Db1 to Db8 to the communication networks Na, Nb, and based on the analysis result, generate action command information, which is information on actions to be performed by the robot device 30, and verbalize (abstract) the generated action command information and transmit it to the communication networks Na, Nb. The drive control units Ca1 to Ca3, Cb1, Cb2 analyze the action command information transmitted from the processing units Pa1 to Pa3, Pb1, Pb2, Pc1 to Pc3 to the communication networks Na, Nb, and control the speaker device 43 and the actuator devices 330a, 330b, 350a, 350b based on the analyzed action command information.

[0073] According to this configuration, since the detection units Da1 to Da5, Db1 to Db8, the processing units Pa1 to Pa3, Pb1, Pb2, Pc1 to Pc3, and the drive control units Ca1 to Ca3, Cb1, Cb2 operate based on the verbalized sensory information and action command information, it is possible to enhance the versatility more than a device that operates with numerical signals or complex control signals such as a conventional control device. In addition, since it is possible to distribute the computing resources, it is also possible to reduce the cost and power consumption. Furthermore, compared with a device that operates with numerical signals or complex control signals, the amount of information to be exchanged between the respective elements can be reduced, so it is also possible to significantly reduce the communication volume.

[0074] The detection units Da1 to Da5, Db1 to Db8 each include sensors 40 to 42, 50 to 59 (sensors for the detection unit), a recognition unit 71 (recognition unit for the detection unit), an assignment unit 75 (generation unit for the detection unit), a verbalization processing unit 76 (abstraction unit for the detection unit), and a communication processing unit 78 (communication unit for the detection unit). The recognition unit 71 recognizes predetermined information detected by the sensors 40 to 42, 50 to 59 based on the detection signals of the sensors 40 to 42, 50 to 59. The assignment unit 75 generates sensory information using the predetermined information recognized by the recognition unit 71. The verbalization processing unit 76 verbalizes (abstracts) the sensory information generated by the assignment unit 75. The communication processing unit 78 transmits the sensory information verbalized (abstracted) by the assignment unit 75 to the communication networks Na, Nb.

[0075] According to this configuration, it becomes possible to verbalize the predetermined information detected by the sensors 40 to 42, 50 to 59 and transmit it to the communication networks Na, Nb.

[0076] The detection units Da1 to Da5, Db1 to Db8 further include a learning unit 72 (learning unit for the detection unit). The learning unit 72 learns the relationship between the detection signals of the sensors 40 to 42, 50 to 59 and the predetermined information detected by the sensors 40 to 42, 50 to 59. The assignment unit 75 generates sensory information using the learning information of the learning unit 72.

[0077] According to this configuration, it becomes possible to generate more accurate sensory information.

[0078] The processing units Pa1 to Pa3, Pb1, Pb2, Pc1 to Pc3 include a communication processing unit 100 (communication unit for processing unit), an analysis unit 105 (analysis unit for processing unit), an action planning unit 106, a self - recognition unit 107, a granting unit 97 (generation unit for processing unit), and a verbalization processing unit 98 (abstraction unit for processing unit). The communication processing unit 100 receives sensory information from the communication networks Na, Nb. The analysis unit 105 analyzes the sensory information received by the communication processing unit 100. The action planning unit 106 plans the actions of the robot device 30 based on the analysis result of the sensory information by the analysis unit 105. The self - recognition unit 107 recognizes the current situation of the robot device 30 based on the analysis result of the sensory information by the analysis unit 105. The granting unit 97 generates action command information using the action plan of the robot device 30 planned by the action planning unit 106 and the current situation of the robot device 30 recognized by the self - recognition unit 107. The verbalization processing unit 98 verbalizes (abstracts) the action command information generated by the granting unit 97. The communication processing unit 100 transmits the action command information verbalized (abstracted) by the verbalization processing unit 98 to the communication networks Na, Nb.

[0079] According to this configuration, it becomes possible to verbalize the action command information generated based on the action plan of the robot device 30 planned by the action planning unit 106 and the current situation of the robot device 30 recognized by the self - recognition unit 107 and transmit it to the communication networks Na, Nb.

[0080] The processing units Pa1 to Pa3, Pb1, Pb2, Pc1 to Pc3 further include an external I / F 90 (external communication unit) and a recognition unit 92 (recognition unit for processing unit). The external I / F 90 receives predetermined external input information transmitted from the external device De. The recognition unit 92 recognizes the predetermined external input information received by the external I / F 90. The granting unit 97 generates action command information using the predetermined external input information recognized by the recognition unit 92.

[0081] According to this configuration, it becomes possible to generate more accurate action command information.

[0082] The processing units Pa1 to Pa3, Pb1, Pb2, Pc1 to Pc3 further include a learning unit 93 (learning unit for the processing unit). The learning unit 93 learns the relationship between the external input information from the external device De and the action command information. The providing unit 97 generates the action command information using the learning information of the learning unit 93.

[0083] According to this configuration, it becomes possible to generate more accurate action command information.

[0084] The drive control units Ca1 to Ca3, Cb1, Cb2 include a communication processing unit 118 (communication unit for the drive unit), an analysis unit 123 (analysis unit for the drive unit), and a control unit 124. The communication processing unit 118 receives the action command information from the communication networks Na, Nb. The analysis unit 123 analyzes the action command information. The control unit 124 controls the speaker device 43 and the actuator devices 330a, 330b, 350a, 350b based on the analysis result of the action command information by the analysis unit 123.

[0085] According to this configuration, it becomes possible to control the speaker device 43 and the actuator devices 330a, 330b, 350a, 350b based on the action command information.

[0086] The drive control units Ca1 to Ca3, Cb1, and Cb2 include a sensor 126 (sensor for drive unit), a recognition unit 111 (recognition unit for drive unit), an imparting unit 115 (generation unit for drive unit), and a verbalization processing unit 116 (abstraction unit for drive unit). The sensor 126 detects at least one of the operating states of the actuator devices 330a, 330b, 350a, 350b and the operating states of the drive targets of the actuator devices 330a, 330b, 350a, 350b. The recognition unit 111 recognizes at least one of the operating states of the actuator devices 330a, 330b, 350a, 350b and the operating states of the drive targets detected by the sensor 126 based on the detection signal of the sensor 126. The imparting unit 115 generates operation result information using at least one of the operating states of the actuator devices 330a, 330b, 350a, 350b and the operating states of the drive targets recognized by the recognition unit 111. The verbalization processing unit 116 verbalizes (abstracts) the operation result information generated by the imparting unit 115. The communication processing unit 118 transmits the operation result information verbalized (abstracted) by the verbalization processing unit 116 to the communication networks Na and Nb.

[0087] According to this configuration, it is possible to verbalize the operation result information generated based on at least one of the operating states of the actuator devices 330a, 330b, 350a, 350b and the operating states of the drive targets and transmit it to the communication networks Na and Nb.

[0088] The drive control units Ca1 to Ca3, Cb1, and Cb2 include a learning unit 112 (learning unit for drive unit). The learning unit 112 learns the relationship between the detection signal of the sensor 126 and at least one of the operating states of the actuator devices 330a, 330b, 350a, 350b and the operating states of the drive targets. The imparting unit 115 generates operation result information based on the learning information of the learning unit 112.

[0089] According to this configuration, it is possible to generate operation result information with higher accuracy.

[0090] <Second Embodiment> Next, the control device 10 of the second embodiment will be described. Hereinafter, the description will focus on the differences from the control device 10 of the first embodiment.

[0091] (Overview of the control device) As shown by the dashed line in FIG. 1, the control device 10 of the present embodiment further includes a plurality of abnormality detection units Dc and a plurality of drive control units Cc during abnormality. The plurality of abnormality detection units Dc and the plurality of drive control units Cc during abnormality are communicably connected via a control signal line Nc. A plurality of high-speed drive control units Ca, a plurality of low-speed drive control units Cb, a plurality of upper processing units Pa, a plurality of middle processing units Pb, and a plurality of lower processing units Pc are connected to the control signal line Nc.

[0092] The abnormality detection unit Dc is a part that detects an abnormality of the mechanical device 20. The abnormality detection unit Dc has a sensor Sc for detecting an abnormality. The sensor Sc is, for example, a battery state sensor that monitors the state of the battery. The abnormality detection unit Dc transmits the abnormality information detected by the sensor Sc to the control signal line Nc.

[0093] When the drive control unit Cc during abnormality receives the abnormality information transmitted from the abnormality detection unit Dc to the control signal line Nc, that is, when any abnormality occurs in the mechanical device 20, it is a part that executes fail-safe control to ensure the safety of the mechanical device 20 or maintain the function of the mechanical device 20. The drive control unit Cc during abnormality controls a fail-safe drive unit Ac provided in the mechanical device 20. The fail-safe drive unit Ac is, for example, a braking device.

[0094] (Specific configurations of the mechanical device and the control device) As shown by the dashed line in FIG. 2, the robot device 30 further includes a battery state sensor 130, an emergency stop switch 131, and a braking device 132.

[0095] The battery state sensor 130 is provided in the battery 38 of the robot device 30 and detects the state of the battery 38.

[0096] The emergency stop switch 131 is a switch that can forcibly stop the robot device 30 by operating it when any abnormality occurs in the robot device 30.

[0097] The brake device 132 is a device that stops the progress of the robot device 30 by generating a braking force on the sole of the foot of the robot device 30. The brake device 132 is used, for example, to prevent the robot device 30 from falling.

[0098] As shown by the dashed line in FIG. 3, the output signal of the emergency stop switch 131 is taken into the upper processing unit Pa1. Further, the upper processing unit Pa1 can directly control the brake device 132 by transmitting a control signal to the brake device 132 via the control signal line Nc.

[0099] The detection signal of the battery state sensor 130 is taken into the upper processing unit Pa3. The upper processing unit Pa3 monitors the state of the battery 38 based on the detection signal of the battery state sensor 130, and when any abnormality occurs in the battery 38, transmits the abnormality information to the control signal line Nc.

[0100] As shown by the dashed line in FIG. 4, the first lower processing unit Pc1 can directly control the brake device 132 by transmitting a control signal to the brake device 132 via the control signal line Nc.

[0101] (Configuration of the processing unit) Next, the configurations of the processing units Pa1 to Pa3, Pb1, Pb2, Pc1 to Pc3 will be described. Since the processing units Pa1 to Pa3, Pb1, Pb2, Pc1 to Pc3 have the same or similar configurations, the configuration of the upper processing unit Pa1 will be described as a representative below.

[0102] As shown in FIG. 12, the upper processing unit Pa1 further includes an abnormality processing unit 108 and an abnormality estimation unit 109.

[0103] When, for example, the emergency stop switch 131 is turned on, the abnormality processing unit 108 receives a notification indicating that the emergency stop switch 131 has been turned on from the emergency stop switch 131 via the control signal line Nc. Further, when an abnormality occurs in the battery 38, the abnormality processing unit 108 receives a notification indicating the same from the upper processing unit Pa3 via the control signal line Nc. The abnormality processing unit 108 transmits these notifications to the abnormality estimation unit 109.

[0104] When the abnormality estimation unit 109 receives a notification indicating that the emergency stop switch 131 has been turned on, or when it receives a notification indicating that an abnormality has occurred in the battery 38, it generates an emergency stop signal for forcibly stopping each part of the robot device 30, and transmits the generated emergency stop signal to the control signal line Nc via the abnormality processing unit 108. When this emergency stop signal is transmitted to the brake device 132 via the control signal line Nc, the brake device 132 is driven and the robot device 30 makes an emergency stop.

[0105] (Configuration of the drive control unit) Next, the configurations of the drive control units Ca1 to Ca3, Cb1, and Cb2 will be specifically described. Since the drive control units Ca1 to Ca3, Cb1, and Cb2 have the same or similar configurations, hereinafter, the configuration of the high-speed drive control unit Ca2 that controls the actuator device 350a of the right hand part 35a will be representatively described.

[0106] As shown in FIG. 13, the high-speed drive control unit Ca2 is further provided with an abnormality processing unit 127. When the abnormality processing unit 127 receives an emergency stop signal via the control signal line Nc, it instructs the control unit 124 to forcibly interrupt and execute the process of forcibly stopping the actuator device 350a. The control unit 124 forcibly stops the actuator device 350a based on the instruction from the abnormality processing unit 127.

[0107] By performing the above processing in the same manner in the other drive control units Ca1, Ca3, Cb1, and Cb2, the speaker device 43 and the actuator devices 330a, 330b, and 350b are also forcibly stopped.

[0108] (Operations and Effects of the Control Device 10 of this Embodiment) As described above, the control device 10 of this embodiment further includes a battery state sensor 130 and an emergency stop switch 131 (abnormality detection unit) for detecting an abnormality of the robot device 30. When an abnormality of the robot device 30 is detected by the battery state sensor 130 or the emergency stop switch 131, each of the drive control units Ca1 to Ca3, Cb1, Cb2 forcibly stops the speaker device 43 and the actuator devices 330a, 330b, 350a, 350b.

[0109] According to such a configuration, it becomes possible to operate the robot device 30 more safely.

[0110] <Third Embodiment> Next, the control device 10 of the third embodiment will be described. Hereinafter, the description will focus on the differences from the control device 10 of the first embodiment.

[0111] (Configuration of the Control Device) As shown in FIG. 14, in the control device 10 of this embodiment, the language conversion unit 76 of the high-speed detection unit Da4 has a first neural network NN10. The first neural network NN10 is a neural network capable of converting the sensory information output from the imparting unit 75 of the high-speed detection unit Da4 into abstracted sensory information. When the language conversion unit 76 inputs the sensory information output from the imparting unit 75 of the high-speed detection unit Da4 to each input layer 2000, the operation result of each intermediate layer 2001 at that time and the configuration information of the first neural network NN10 when the operation result is obtained are transmitted to the high-speed side communication network Na via the data output unit 77 and the communication processing unit 78.

[0112] The configuration information of the first neural network NN10 includes information on the connection weights between the nodes of each layer, for example, the connection weights wa 11 ~wa 1n , ···, wa m1 ~wamn It contains the information. Here, m and n are arbitrary natural numbers. Further, the configuration information of the first neural network NN10 includes information on the connection destinations between the nodes of each layer, for example, information indicating to which of the plurality of output layers 2002 each of the plurality of intermediate layers 2001 is connected.

[0113] As shown in FIG. 14, the verbalization processing unit 98 of the median processing unit Pb1 similarly has the first neural network NN10. When the verbalization processing unit 98 acquires the configuration information of the first neural network NN10 from the high-speed communication network Na via the communication processing unit 100 and the data reception unit 101, it reflects the configuration information in its own first neural network NN10. As a result, the first neural network NN10 possessed by the verbalization processing unit 76 of the high-speed detection unit Da4 and the first neural network NN10 possessed by the verbalization processing unit 98 of the median processing unit Pb1 have the same configuration.

[0114] Further, after the verbalization processing unit 98 shares the configuration of the first neural network NN10 with the verbalization processing unit 76 of the high-speed detection unit Da4 in this way, when it acquires the calculation results of each intermediate layer 2001 from the high-speed communication network Na via the communication processing unit 100 and the data reception unit 101, it reflects the calculation results of each intermediate layer 2001 in its own first neural network NN10, thereby acquiring abstracted sensory information from each output layer 2002.

[0115] On the other hand, as shown in FIG. 15, in the control device 10 of the present embodiment, the linguification processing unit 98 of the median processing unit Pb1 has a second neural network NN20. The second neural network NN20 is a neural network capable of converting the action command information output from the application unit 97 of the median processing unit Pb1 into abstracted action command information. When the linguification processing unit 98 inputs the action command information output from the application unit 97 of the median processing unit Pb1 to each input layer 3000, the operation result of each intermediate layer 3001 at that time and the configuration information of the second neural network NN20 when the operation result is obtained are transmitted to the high-speed communication network Na via the data output unit 99 and the communication processing unit 100.

[0116] The configuration information of the second neural network NN20 includes information on the connection weights between the nodes of each layer, for example, the connection weights wb 11 ~wb 1q ,···,wb p1 ~wb pq of the nodes between a plurality of intermediate layers 3001 and a plurality of output layers 3002. Here, p and q are arbitrary natural numbers. The configuration information of the second neural network NN20 also includes information on the connection destinations between the nodes of each layer, for example, information indicating which of the plurality of output layers 3002 each of the plurality of intermediate layers 3001 is connected to.

[0117] As shown in FIG. 15, the linguification processing unit 116 of the high-speed drive control unit Ca2 similarly has a second neural network NN20. When the linguification processing unit 116 acquires the configuration information of the second neural network NN20 transmitted from the median processing unit Pb1 from the high-speed communication network Na via the communication processing unit 118 and the data receiving unit 119, it reflects the configuration information in its own second neural network NN20. As a result, the second neural network NN20 possessed by the linguification processing unit 98 of the median processing unit Pb1 and the second neural network NN20 possessed by the linguification processing unit 116 of the high-speed drive control unit Ca2 have the same configuration.

[0118] Further, after the language conversion processing unit 116 shares the configuration of the second neural network NN20 with the language conversion processing unit 98 of the intermediate processing unit Pb1 in this way, when the operation results of each intermediate layer 3001 transmitted from the intermediate processing unit Pb1 are obtained via the high-speed communication network Na through the communication processing unit 118 and the data receiving unit 119, the operation results of each intermediate layer 3001 are reflected in its own second neural network NN20, so as to obtain abstracted action command information from each output layer 3002.

[0119] Note that the other detection units Da1 to Da3, Da5, Db1 to Db8 may have the same or similar configuration as the high-speed detection unit Da4. Also, the other processing units Pa1 to Pa3, Pb2, Pc1 to Pc3 may have the same or similar configuration as the intermediate processing unit Pb1. Further, the other drive control units Ca1, Ca3, Cb1, Cb2 may have the same or similar configuration as the high-speed drive control unit Ca2.

[0120] (Operations and Effects of the Control Device 10 of the Present Embodiment) As described above, the high-speed detection unit Da4 of the present embodiment has the input layer 2000 and the intermediate layer 2001 of the first neural network NN10 for abstracting sensory information, and transmits the operation result of the intermediate layer 2001 when the sensory information is input to the input layer 2000 to the high-speed communication network Na (transmission path). The intermediate processing unit Pb1 has the intermediate layer 2001 and the output layer 2002 of the first neural network NN10, and obtains abstracted sensory information from the output layer 2002 using the operation result of the intermediate layer 2001 transmitted to the high-speed communication network Na by the high-speed detection unit Da4.

[0121] Even with such a configuration, it is possible to easily obtain the abstracted sensory information.

[0122] The middle processing unit Pb1 of this embodiment has an input layer 3000 and an intermediate layer 3001 of the second neural network NN20 for abstracting action command information, and transmits the calculation result of the intermediate layer 3001 when the action command information is input to the input layer 3000 to the high-speed communication network Na (transmission line). The high-speed drive control unit Ca2 has an intermediate layer 3001 and an output layer 3002 of the second neural network NN20, and obtains the abstracted action command information from the output layer 3002 using the calculation result of the intermediate layer 3001 transmitted to the high-speed communication network Na by the middle processing unit Pb1.

[0123] Even with such a configuration, it is possible to obtain the abstracted action command information.

[0124] <Other Embodiments> The present disclosure is not limited to the above specific examples.

[0125] For example, the configuration of the above control device 10 is not limited to the humanoid robot device 30, and is also applicable to industrial robots and the like. Further, the configuration of the above control device 10 is not limited to robots, and can also be applied to any mechanical device.

[0126] Instead of the process of verbalizing various information, the language processing units 76, 98, and 116 may execute, for example, a process of compressing various information or a process of symbolizing various information.

[0127] Those in which those skilled in the art appropriately make design changes to the above specific examples are also included in the scope of the present disclosure as long as they have the features of the present disclosure. Each element included in each of the above-described specific examples, and its arrangement, conditions, shape, etc. are not limited to those illustrated and can be changed as appropriate. Each element included in each of the above-described specific examples can be combined as appropriate as long as no technical contradiction occurs.

[0128] The neural network NN of each embodiment is not limited to having a single intermediate layer 1001, and may have a plurality of intermediate layers. For example, when the neural network NN is a convolutional neural network (CNN), it may have a convolutional layer, a pooling layer, a fully connected layer, etc. as intermediate layers. The same applies to the first neural network NN10 and the second neural network NN20 of the third embodiment.

Description of reference numerals

[0129] Aa: High-speed drive unit, Ab: Low-speed drive unit, Ca, Ca1~Ca3: High-speed drive control units, Cb, Cb1, Cb2: Low-speed drive control units, Da, Da1~Da5: High-speed detection units, Db, Db1~Db8: Low-speed detection units, Na: High-speed side communication network (transmission line), Nb: Low-speed side communication network (transmission line), Pa, Pa1~Pa3: Upper processing units, Pb, Pb1, Pb2: Middle processing units, Pc, Pc1~Pc3: Lower processing units, Sa, Sb: Sensors (sensors for detection units), 10: Control device, 20: Mechanical device, 30: Robot device (mechanical device), 40: Camera sensor (sensor for detection units), 41: Distance measurement sensor (sensor for detection units), 42: Voice sensor (sensor for detection units), 43: Speaker device (drive unit), 50~59: Contact sensors (sensors for detection units), 71: Recognition unit (recognition unit for detection units), 72: Learning unit (learning unit for detection units), 75: Assignment unit (generation unit for detection units), 76: Verbalization processing unit (abstraction unit for detection units), 78: Communication processing unit (communication unit for detection units), 90: External I / F (external communication unit), 92: Recognition unit (recognition unit for processing units), 93: Learning unit (learning unit for processing units), 97: Assignment unit (generation unit for processing units), 98: Verbalization processing unit (abstraction unit for processing units), 100: Communication processing unit (communication unit for processing units), 105: Analysis unit (analysis unit for processing units), 106: Action planning unit, 107: Self-recognition unit, 111: Recognition unit (recognition unit for drive units), 112: Learning unit (learning unit for drive units), 115: Assignment unit (generation unit for drive units), 116: Verbalization processing unit (abstraction unit for drive units), 118: Communication processing unit (communication unit for drive units), 123: Analysis unit (analysis unit for drive units), 124: Control unit, 126: Sensor (sensor for drive units), 330a, 330b, 350a, 350b: Actuator devices (drive units).

Claims

1. A control device that controls a mechanical device provided with a plurality of drive units, a detection unit that converts a detection signal output from a detection unit sensor provided in the mechanical device into sensory information when the detection unit sensor detects predetermined information, and verbalizes the converted sensory information into a predetermined language and transmits the converted sensory information to a transmission path; a processing unit that analyzes the verbalized sensory information transmitted from the detection unit to the transmission path, generates action command information that is information on an action to be taken by the mechanical device based on an analysis result of the sensory information, and transmits the generated action command information to the transmission path; a drive control unit that analyzes the action command information transmitted from the processing unit to the transmission path and controls the drive unit based on the analyzed action command information. Control device.

2. The detection unit a sensor for the detection unit; a detector recognition unit that recognizes the predetermined information detected by the detector sensor based on a detection signal from the detector sensor; a generation unit for the detection unit that generates the sensory information using the predetermined information recognized by the recognition unit for the detection unit; a detection unit verbalization unit that verbalizes the sensory information generated by the detection unit generation unit into the predetermined language; a detection unit communication unit that transmits the sensory information verbalized by the detection unit verbalization unit to the transmission path. The control device according to claim 1 .

3. the detection unit further includes a detection unit learning unit that learns a relationship between the detection signal of the detection unit sensor and the predetermined information detected by the detection unit sensor, The detection unit generation unit generates the sensory information by further using learning information from the detection unit learning unit. The control device according to claim 2 .

4. The detection unit recognition unit, the detection unit verbalization unit, and the detection unit learning unit are configured by neural networks. The control device according to claim 3 .

5. The processing unit a processing unit communication unit that receives the sensory information from the transmission path; an analysis unit for the processing unit that analyzes the sensory information received by the communication unit for the processing unit; an action planning unit that plans an action of the mechanical device based on the analysis result of the sensory information by the processing unit analysis unit; a self-recognition unit that recognizes a current state of the mechanical device based on the analysis result of the sensory information by the processing unit analysis unit; a generation unit for a processing unit that generates the action command information using the action plan of the machine device planned by the action planning unit and the current situation of the machine device recognized by the self-recognition unit; a processing unit languageization unit that languageizes the action command information generated by the processing unit generation unit into the predetermined language, The processing unit communication unit transmits the action command information verbalized by the processing unit verbalization unit to the transmission path. The control device according to claim 1 .

6. The processing unit an external communication unit that receives external input information transmitted from an external device; a processing unit recognition unit that recognizes the external input information received by the external communication unit, The processing unit generation unit generates the action command information by further using the external input information recognized by the processing unit recognition unit. The control device according to claim 5 .

7. the processing unit further includes a processing unit learning unit that learns a relationship between the external input information and the action command information, The processing unit generation unit generates the action command information by further using learning information from the processing unit learning unit. The control device according to claim 6.

8. The processing unit recognition unit, the processing unit verbalization unit, and the processing unit learning unit are configured by neural networks. The control device according to claim 7.

9. The drive control unit a communication unit for the driving unit that receives the action command information from the transmission path; an analysis unit for a driving unit that analyzes the action command information; a control unit that controls the drive unit based on an analysis result of the action command information by the drive unit analysis unit. The control device according to claim 1 .

10. The drive control unit a drive unit sensor that detects at least one of an operating state of the drive unit and an operating state of an object moved by the drive unit; a drive unit recognition unit that recognizes at least one of the operation of the drive unit and the operation of the object detected by the drive unit sensor based on a detection signal from the drive unit sensor; a generator for driver that generates operation result information using at least one of the operation of the driver and the operation of the object recognized by the recognizer for driver; a driver languageization unit that languageizes the operation result information generated by the driver language generation unit into the predetermined language, The drive unit communication unit transmits the operation result information verbalized by the drive unit verbalization unit to the transmission path. The control device according to claim 9.

11. the control unit further includes a drive unit learning unit that learns a relationship between the detection signal of the drive unit sensor and at least one of an operation of the drive unit and an operation of the object; The driver generation unit generates the operation result information by further using learning information from the driver learning unit. The control device according to claim 10.

12. The drive unit recognition unit, the drive unit verbalization unit, and the drive unit learning unit are configured by neural networks. The control device according to claim 11.

13. The processing units include a plurality of lower-level processing units, a plurality of middle-level processing units whose processing has priority over the lower-level processing units, and a plurality of upper-level processing units whose processing has priority over the lower-level processing units and the middle-level processing units. The control device according to claim 1 .

14. The detector includes a plurality of low-speed detectors and a plurality of high-speed detectors that operate faster than the low-speed detectors. The control device according to claim 1 .

15. The drive control unit includes a plurality of low-speed drive control units and a plurality of high-speed drive control units that operate at a higher speed than the low-speed drive control units. The control device according to claim 1 .

16. further comprising an abnormality detection unit that detects an abnormality in the mechanical device; The drive control unit forcibly stops the drive unit when the abnormality detection unit detects an abnormality in the mechanical device. The control device according to claim 1 .

17. the detection unit has an input layer and an intermediate layer of a first neural network for verbalizing the sensory information into the predetermined language, and transmits a calculation result of the intermediate layer when the sensory information is input to the input layer to the transmission path; The processing unit has the intermediate layer and the output layer of the first neural network, and acquires the sensory information, which is verbalized in the predetermined language, from the output layer using the calculation result of the intermediate layer transmitted to the transmission path by the detection unit. The control device according to claim 1 .

18. the processing unit has an input layer and an intermediate layer of a second neural network for verbalizing the action command information into the predetermined language, and transmits a calculation result of the intermediate layer when the action command information is input to the input layer to the transmission path; The drive control unit has the intermediate layer and the output layer of the second neural network, and acquires the action command information, which is verbalized in the predetermined language, from the output layer using the calculation result of the intermediate layer transmitted to the transmission path by the processing unit. The control device according to claim 1 .

Images