JP4449372B2 - Robot apparatus and behavior control method thereof - Google Patents

Description

  The present invention relates to a robot apparatus that performs autonomous operation and realizes realistic communication, and its action control method, and in particular, a function of recognizing an external situation such as an image or sound and reflecting its own action on it. The present invention relates to an autonomous robot apparatus provided with the above and an action control method thereof.

  A mechanical device that performs an action similar to that of a human (living body) using an electrical or magnetic action is called a “robot”. Robots have begun to spread in Japan since the late 1960s, but many of them are industrial robots such as manipulators and transfer robots for the purpose of automating and unmanned production work in factories. Met.

  Recently, practical robots that support life as a human partner, that is, support human activities in various situations in daily life such as the living environment, have been developed. Unlike industrial robots, such practical robots have the ability to learn how to adapt themselves to humans with different personalities or to various environments in various aspects of the human living environment. For example, it was designed based on the body mechanism and motion of a “pet-type” robot that imitates the body mechanism and movement of a quadruped animal such as a dog or cat, or a human who walks upright on two legs. Robotic devices such as “humanoid” or “humanoid” robots are already in practical use.

  Since these robot devices can perform various operations with an emphasis on entertainment performance as compared with industrial robots, they may be referred to as entertainment robots. In addition, there is a robot apparatus that operates autonomously according to information from the outside or an internal state.

  In general, such an autonomous robot apparatus selects actions sequentially according to changes in the external environment such as vision and hearing. Another example of the action selection mechanism is to model emotions such as instinct and emotion, manage the internal state of the system, and select an action according to a change in the internal state. Note that the internal state of the system changes depending on changes in the external environment and manifesting selected actions.

  By the way, when designing the behavior of the robot apparatus, it is necessary to consider resources such as hardware and software of the robot apparatus and the required behavior, and therefore, the behavior module is often realized on demand.

  The actual design could be monolithic, i.e. the entire behavior of the robotic device could be realized with a single software module, but in order to achieve more complex behavior, modularization, i.e. It is also possible to disassemble the unit and realize the entire action by the interaction (for example, see Patent Document 1 below).

JP 2003-111981

  However, in the past, when trying to use a unit to achieve another action, the unit's interaction procedure and the unit itself may have to be fundamentally rewritten, and unit recombination There was a problem that it was difficult.

  The present invention has been proposed in view of such conventional situations, and provides a robot apparatus and a behavior control method for realizing a complex action by a plurality of action modules and facilitating recombination of units. With the goal.

In order to achieve the above-described object, a robot apparatus according to the present invention includes a movable part control means for controlling the movable part and a plurality of behavior modules in a tree structure format in a robot apparatus having a movable part. has been a motion determination unit, the behavior module has a storage means for storing defined by control policies connection pattern for executing one or more lower-level behavior modules to be connected thereto independently, the The one or more lower-order behavior modules include the execution request degree of the behavior of the one or more lower-order behavior modules themselves calculated based on the external stimulus and the internal state, and the ones required for the execution of the one or more lower-order behavior modules themselves. convey information about the hardware resources of the robot apparatus to the upper action module to which the one or more lower-level behavior modules are connected, the upper Top action module, and the information transmitted from the one or more subordinate action module, and to the resources needed to run the action module itself execution request of the said upper action of the upper position of the action module itself Based on the information and the control policy , the resources necessary for the execution of the higher-level action module itself are excluded from one or more lower-level action modules to one or more lower-level action modules that can distribute the resource. the remaining controls to distribute resources, the movable part controlling means is for the upper action module or the one or more subordinate action modules based on the determined action, for controlling the movable portion .

In order to achieve the above-described object, the behavior control method according to the present invention is a behavior control method for a robot apparatus having a movable part, wherein the behavior determination means has a plurality of behavior modules as nodes and is used as a higher-order behavior module. One or more subordinate behavior modules are connected in a tree structure, and the one or more subordinate behavior modules are calculated based on an external stimulus and an internal state. A step of transmitting information about the execution request level of the action and the hardware resources of the robot apparatus necessary for the execution of the one or more lower-order action modules to the higher-order action module; The information transmitted from the one or more lower-level behavior modules, the higher-level behavior module's own behavior execution request level, and the Information about and the resources needed to run the position of action module itself, based on the control policy which defines the connection pattern for independently executing the one or more subordinate action module stored in the storage means, Control is performed so that the remaining resources excluding resources necessary for the execution of the higher-level action module itself are distributed to one or more lower-level action modules capable of distributing the resources among the one or more lower-level action modules. And a step of controlling the movable part based on an action determined by the upper action module or the one or more lower action modules.

  In such a robot apparatus and its behavior control method, among the plurality of behavior modules configured in a tree structure format, the higher-order behavior module is connected to itself based on the control policy stored in the storage means. The above behavior module is controlled.

  In the robot apparatus and the behavior control method thereof according to the present invention, the higher-order behavior module among the plurality of behavior modules configured in the tree structure format is connected to itself based on the control policy stored in the storage unit. Since one or more behavior modules are controlled, the independence of each behavior module can be increased, and thus the tree structure of the behavior modules can be easily recombined.

  Hereinafter, specific embodiments to which the present invention is applied will be described in detail with reference to the drawings.

  The biped walking type robot apparatus shown as an example of the present invention is a practical robot that supports human activities in various situations in the living environment and other daily life, and has an internal state (anger, sadness, joy, fun) Etc.), it is an entertainment robot that can express basic actions performed by humans.

  As shown in FIG. 1, the robot apparatus 1 includes a head unit 3 connected to a predetermined position of the trunk unit 2, and two left and right arm units 4R / L and two right and left leg units 5R /. L is connected to each other (provided that R and L are suffixes indicating right and left, respectively, and the same applies hereinafter).

  The joint degree-of-freedom configuration of the robot apparatus 1 is schematically shown in FIG. The neck joint that supports the head unit 3 has three degrees of freedom: a neck joint yaw axis 101, a neck joint pitch axis 102, and a neck joint roll axis 103.

  Each arm unit 4R / L constituting the upper limb includes a shoulder joint pitch axis 107, a shoulder joint roll axis 108, an upper arm yaw axis 109, an elbow joint pitch axis 110, a forearm yaw axis 111, A wrist joint pitch axis 112, a wrist joint roll axis 113, and a hand part 114 are configured. The hand portion 114 is actually a multi-joint / multi-degree-of-freedom structure including a plurality of fingers. However, since the operation of the hand 114 has little contribution or influence on the posture control or walking control of the robot apparatus 1, it is assumed in this specification that the degree of freedom is zero. Therefore, it is assumed that each arm portion has seven degrees of freedom.

  The trunk unit 2 has three degrees of freedom: a trunk pitch axis 104, a trunk roll axis 105, and a trunk yaw axis 106.

  Each leg unit 5R / L constituting the lower limb includes a hip joint yaw axis 115, a hip joint pitch axis 116, a hip joint roll axis 117, a knee joint pitch axis 118, an ankle joint pitch axis 119, and an ankle joint. A roll shaft 120 and a foot 121 are included. In the present specification, the intersection of the hip joint pitch axis 116 and the hip joint roll axis 117 defines the hip joint position of the robot apparatus 1. The foot 121 of the human body is actually a structure including a multi-joint / multi-degree-of-freedom sole, but the foot of the robot apparatus 1 has zero degrees of freedom. Accordingly, each leg is configured with 6 degrees of freedom.

  In summary, the robot apparatus 1 as a whole has a total of 3 + 7 × 2 + 3 + 6 × 2 = 32 degrees of freedom. However, the robot device 1 for entertainment is not necessarily limited to 32 degrees of freedom. Needless to say, the degree of freedom, that is, the number of joints, can be increased or decreased as appropriate in accordance with design / production constraints or required specifications.

  Each degree of freedom of the robot apparatus 1 as described above is actually implemented using an actuator. It is preferable that the actuator be small and light in light of demands such as eliminating the appearance of extra bulges on the appearance and approximating the shape of a human body, and performing posture control on an unstable structure such as biped walking. .

  FIG. 3 schematically shows a control system configuration of the robot apparatus 1. As shown in the figure, the robot apparatus 1 includes a trunk unit 2, a head unit 3, an arm unit 4R / L, and a leg unit 5R / L representing human limbs, and coordinated operations between the units. It is comprised with the control unit 10 which performs the adaptive control for implement | achieving.

  The operation of the entire robot apparatus 1 is controlled in an integrated manner by the control unit 10. The control unit 10 includes data of a main control unit 11 constituted by main circuit components (not shown) such as a CPU (Central Processing Unit), DRAM, flash ROM, etc., and data of each component of the power supply circuit and the robot apparatus 1. The peripheral circuit 12 includes an interface (not shown) for sending and receiving commands.

  In realizing the present invention, the installation location of the control unit 10 is not particularly limited. Although it is mounted on the trunk unit 2 in FIG. 3, it may be mounted on the head unit 3. Alternatively, the control unit 10 may be provided outside the robot apparatus 1 so as to communicate with the body of the robot apparatus 1 by wire or wirelessly.

Each joint freedom degree in the robot apparatus 1 shown in FIG. 2 is implement | achieved by the actuator corresponding to each. That is, the head unit 3 includes a neck joint yaw axis actuator A ₂ , neck joint pitch axis actuator A ₃ , neck joint roll representing the neck joint yaw axis 101, neck joint pitch axis 102, and neck joint roll axis 103. axis actuator A ₄ is disposed.

  In addition, the head unit 3 is provided with a CCD (Charge Coupled Device) camera for imaging an external situation, a distance sensor for measuring the distance to an object located in front, and an external sound. A microphone for collecting sound, a speaker for outputting sound, a touch sensor for detecting pressure received by a physical action such as “blowing” or “striking” from a user, and the like are provided.

The trunk unit 2 includes a trunk pitch axis actuator A ₅ , a trunk roll axis actuator A ₆ , a trunk yaw representing the trunk pitch axis 104, trunk roll axis 105, and trunk yaw axis 106. axis actuator A ₇ is disposed. In addition, the trunk unit 2 includes a battery serving as a starting power source for the robot apparatus 1. This battery is constituted by a chargeable / dischargeable battery.

The arm unit 4R / L is subdivided into an upper arm unit 4 ₁ R / L, an elbow joint unit 4 ₂ R / L, and a forearm unit 4 ₃ R / L. Shoulder joint pitch axis actuator A ₈ , shoulder joint roll axis actuator A ₈ representing the joint roll axis 108, upper arm yaw axis 109, elbow joint pitch axis 110, forearm yaw axis 111, wrist joint pitch axis 112, and wrist joint roll axis 113. _9. Upper arm yaw axis actuator A ₁₀ , elbow joint pitch axis actuator A ₁₁ , elbow joint roll axis actuator A ₁₂ , wrist joint pitch axis actuator A ₁₃ , and wrist joint roll axis actuator A ₁₄ are provided.

The leg unit 5R / L is subdivided into a thigh unit 5 ₁ R / L, a knee unit 5 ₂ R / L, and a shin unit 5 ₃ R / L. Hip joint yaw axis actuator A ₁₆ , hip joint pitch axis actuator A ₁₇ , hip joint roll axis actuator representing each of hip joint pitch axis 116, hip joint roll axis 117, knee joint pitch axis 118, ankle joint pitch axis 119, and ankle joint roll axis 120. A ₁₈ , knee joint pitch axis actuator A ₁₉ , ankle joint pitch axis actuator A ₂₀ , and ankle joint roll axis actuator A ₂₁ are provided. The actuators A ₂ , A ₃ ... Used for each joint are more preferably composed of small AC servo actuators of the type that are directly connected to gears and that are mounted on the motor unit with the servo control system integrated into a single chip. can do.

  For each mechanism unit such as the trunk unit 2, the head unit 3, each arm unit 4R / L, each leg unit 5R / L, the sub-control units 20, 21, 22R / L, 23R of the actuator drive control unit / L is deployed. Furthermore, a grounding confirmation sensor 30R / L for detecting whether or not the foot of each leg unit 5R / L has landed is mounted, and a posture sensor 31 for measuring the posture is provided in the trunk unit 2. is doing.

  The grounding confirmation sensor 30R / L is configured by, for example, a proximity sensor or a micro switch installed on the sole of the foot. In addition, the posture sensor 31 is configured by a combination of an acceleration sensor and a gyro sensor, for example.

  Based on the output of the ground contact confirmation sensor 30R / L, it is possible to determine whether the left and right legs are currently standing or swinging during an operation period such as walking or running. Further, the inclination and posture of the trunk can be detected by the output of the posture sensor 31.

  The main control unit 11 can dynamically correct the control target in response to the outputs of the sensors 30R / L, 31. More specifically, the whole body that performs adaptive control on each of the sub-control units 20, 21, 22R / L, and 23R / L, and the upper limbs, trunk, and lower limbs of the robot apparatus 1 are cooperatively driven. A movement pattern can be realized.

For the whole body motion on the body of the robot device 1, set the foot motion, ZMP (Zero Moment Point) trajectory, trunk motion, upper limb motion, waist height, etc., and instruct the operation according to these settings The command to be transferred is transferred to each sub-control unit 20, 21, 22R / L, 23R / L. Each sub-control unit 20, 21,... Interprets a received command from the main control unit 11 and outputs a drive control signal to each actuator A ₂ , A _3. . Here, “ZMP” is a point on the floor where the moment due to floor reaction force during walking is zero, and “ZMP trajectory” is, for example, during the walking operation period of the robot apparatus 1. It means the trajectory that ZMP moves. Regarding the concept of ZMP and its application to the stability criteria for walking robots, Miomir Vukobratovic “LEGGED LOCOMOTION ROBOTS” (Ichiro Kato's “Walking Robots and Artificial Feet” (Nikkan Kogyo Shimbun)) It is described in.

As described above, in the robot apparatus 1, each of the sub-control units 20, 21,... Interprets the received command from the main control unit 11, and applies to each actuator A ₂ , A _3. Drive control signals are output to control the drive of each unit. Thereby, the robot apparatus 1 can stably transition to the target posture and can walk in a stable posture.

  In addition to the attitude control as described above, the control unit 10 in the robot apparatus 1 receives various sensors such as an acceleration sensor, a touch sensor, and a grounding confirmation sensor, image information from a CCD camera, audio information from a microphone, and the like. It is integrated and processed. In the control unit 10, although not shown, various sensors such as an acceleration sensor, a gyro sensor, a touch sensor, a distance sensor, a microphone, and a speaker, each actuator, a CCD camera, and a battery are connected to the main control unit 11 via corresponding hubs. Has been.

  The main control unit 11 sequentially takes in sensor data, image data, and audio data supplied from the above-described sensors, and sequentially stores them in a predetermined position in the DRAM via the internal interface. The main control unit 11 sequentially takes in battery remaining amount data representing the remaining amount of battery supplied from the battery and stores it in a predetermined position in the DRAM. Each sensor data, image data, audio data, and battery remaining amount data stored in the DRAM is used when the main control unit 11 controls the operation of the robot apparatus 1.

  The main control unit 11 reads the control program and stores it in the DRAM at the initial stage when the power of the robot apparatus 1 is turned on. In addition, the main control unit 11 determines whether the main control unit 11 itself or the surrounding situation or the user based on each sensor data, image data, audio data, and battery remaining amount data sequentially stored in the DRAM from the main control unit 11. Judgment of whether or not there is an instruction and action.

  Furthermore, the main control unit 11 determines an action according to its own situation based on the determination result and a control program stored in the DRAM, and drives a necessary actuator based on the determination result, thereby driving the robot apparatus 1. To take actions such as “gesture” and “hand gesture”.

  In this way, the robot apparatus 1 can perform behavior control according to the recognition result of the external stimulus and the change in the internal state based on the control program. FIG. 4 schematically shows the basic architecture of the behavior control system 50 employed in the robot apparatus 1.

  The illustrated behavior control system 50 can employ object-oriented programming. In this case, each software is handled in units of modules called “objects” in which data (properties) and processing procedures (methods) for the data are integrated. In addition, each object can perform property passing and method inheritance by message communication and an inter-object communication method using a shared memory.

  The behavior control system 50 includes a visual recognition function unit 51, an auditory recognition function unit 52, and a contact recognition function unit 53 in order to recognize an external environment (Environment) 61.

  The visual recognition function unit (Video) 51 performs image recognition processing such as face recognition and color recognition and feature extraction based on a photographed image input via an image input device such as a CCD camera. The visual recognition function unit 51 includes a plurality of objects such as “MultiColorTracker”, “FaceDetector”, and “FaceIdentify” which will be described later.

  The auditory recognition function unit (Audio) 52 performs voice recognition on voice data input via a voice input device such as a microphone, and performs feature extraction or word set (text) recognition. The auditory recognition function unit 52 includes a plurality of objects such as “AudioRecog” and “SpeechRecog” described later.

  The contact recognition function unit (Tactile) 53 recognizes an external stimulus such as “struck” or “struck” by recognizing a sensor signal from a touch sensor built in the head of the aircraft, for example.

  The internal state management unit (ISM: InternalStatusManager) 54 includes an instinct model and an emotion model, and external stimuli (ES: recognized by the visual recognition function unit 51, the auditory recognition function unit 52, and the contact recognition function unit 53 described above. The internal state of the robot apparatus 1 such as instinct and emotion is managed according to (ExternalStimula).

  The emotion model and the instinct model have the recognition result and the action history as inputs, respectively, and manage the emotion value and the instinct value. The behavior model can refer to these emotion values and instinct values.

  The short term memory unit (ShortTermMemory) 55 is a functional module that holds targets and events recognized from the external environment by the visual recognition function unit 51, the auditory recognition function unit 52, and the contact recognition function unit 53 for a short period of time. For example, the input image from the CCD camera is stored for a short period of about 15 seconds.

  A long term memory (LongTermMemory) 56 is used to hold information obtained by learning such as the name of an object for a long period of time. For example, the long-term storage unit 56 associates and stores a change in the internal state from an external stimulus in a certain behavior module.

  The behavior control of the robot apparatus 1 is performed by the “reflex behavior” realized by the reflex behavior unit 59, the “situation-dependent behavior” realized by the situation-dependent behavior hierarchy 58, and the “contemplation behavior” realized by the consideration behavior hierarchy 57. It is divided roughly into.

  The deliberation action layer (DeliberativeLayer) 57 performs a relatively long-term action plan of the robot apparatus 1 based on the storage contents of the short-term storage unit 55 and the long-term storage unit 56.

  The contemplation action is an action performed by inference and a plan for realizing it by a given situation or a command from a human. Such inferences and plans require more processing time and computational load than reaction time for maintaining interaction. Therefore, the robot apparatus 1 performs reflex behavior and situation-dependent behavior in real time to respond to the contemplation behavior. Make a plan.

  The situation dependent behavior hierarchy (SBL: SituatedBehaviorsLayer) 58 is where the robot apparatus 1 is currently placed based on the storage contents of the short-term storage unit 55 and the long-term storage unit 56 and the internal state managed by the internal state management unit 54. Control behavior in response to the situation.

  The state-dependent action hierarchy 58 prepares a state machine for each action, classifies recognition results of external information input from the sensor, and expresses the action on the aircraft depending on the previous action and situation. To do. The situation-dependent action hierarchy 58 also realizes an action for keeping the internal state within a certain range (also referred to as “homeostasis action”). When the internal state exceeds the specified range, the internal state is The action is activated so that the action for returning to the range can be easily performed (actually, the action is selected in consideration of both the internal state and the external environment). Situation-dependent behavior has a slower reaction time than reflex behavior (described later).

  The reflexive action unit (Reflexive SBL) 59 is a functional module that realizes a reflexive body operation in response to an external stimulus recognized by the visual recognition function unit 51, the auditory recognition function unit 52, and the contact recognition function unit 53 described above. It is.

  The reflex action is basically an action that directly receives the recognition result of the external information input from the sensor, classifies it, and directly determines the output action. For example, it is preferable to implement the behavior of avoiding detected obstacles as a reflex behavior.

  In the robot apparatus 1 according to the present embodiment, the short-term storage unit 55 temporally and spatially displays the results of a plurality of recognizers such as the visual recognition function unit 51, the auditory recognition function unit 52, and the contact recognition function unit 53 described above. Integration is performed so as to maintain consistency, and the perception of each object in the external environment is provided as a short-term memory to the context-dependent action hierarchy (SBL) 58 or the like. The recognition result of the external information inputted from the sensor is directly provided to the reflexive action unit (Reflexive SBL) 59.

  In general, if there are only the situation-dependent action hierarchy (SBL) 58 and the contemplation action hierarchy 57 that determine the action in consideration of various conditions, the reaction of the robot becomes slow. Therefore, the behavior control system 50 of the robot apparatus 1 according to the present embodiment determines the expression of the behavior in consideration of various conditions (internal state and external state), so that the situation-dependent behavior hierarchy (SBL) 58 is determined. In addition to the contemplation action hierarchy 57, a reflexive action part (Reflexive SBL) 59 that determines the expression of action under a certain single sensor condition is also configured as a separate process.

Note that the above-described contemplation action hierarchy 57, situation-dependent action hierarchy (SBL) 58, and reflex action section (Reflexive SBL) 59 can be described as higher-level application programs that are independent of the hardware configuration of the robot apparatus 1. . On the other hand, the hardware-dependent action control unit (ConfigurationDependentActionAndReactions) 60 performs driving of the above-described actuators A ₂ , A ₃ ... According to a command from these higher-level applications (action modules called “schema”). Operate the aircraft hardware (external environment) directly.

  Here, each functional module in the behavior control system 50 of the robot apparatus 1 as shown in FIG. 4 is configured as an object. Each object passes data (property) and inherits a program (method) that describes the behavior of the object by message communication and communication method between objects using shared memory. Hereinafter, the function of each object will be described with reference to FIG. 5 schematically showing the object configuration in the behavior control system 50.

Visual recognition functional unit 51, "FaceDetector", "MultiColo r Tracker", it consists of three objects called "FaceIdentify". FaceDetector is an object that detects a face area from an image frame, and outputs the detection result to FaceIdentify. The MultiColorTracker is an object that performs color recognition, and outputs a recognition result to FaceIdentify and ShortTermMemory (an object constituting the short-term storage unit 55). FaceIdentify also identifies a person by searching for a detected face image in a personal dictionary, and outputs the person ID information to the ShortTermMemory along with the position and size information of the face image area.

  The auditory recognition function unit 52 includes two objects “AudioRecog” and “SpeechRecog”. AudioRecog is an object that receives voice data from a voice input device such as a microphone and performs feature extraction and voice section detection, and outputs the feature amount and sound source direction of the voice data in the voice section to SpeechRecog and ShortTermMemory. SpeechRecog is an object that performs speech recognition using the speech feature value, speech dictionary, and syntax dictionary received from AudioRecog, and outputs a set of recognized words to ShortTermMemory.

  The contact recognition function unit 53 includes an object “TactileSensor” that recognizes a sensor input from the touch sensor, and outputs a recognition result to ShortTermMemory and an InternalStatusManager (ISM) that is an object for managing an internal state.

  ShortTermMemory (STM) is an object that constitutes the short-term memory unit 55, and holds targets and events recognized from the external environment by each object of the recognition system described above (for example, an input image from a CCD camera is about 15 seconds). It is a functional module that stores only for a short period of time, and periodically notifies the Stimulated SituatedBehaviorsLayer as an external stimulus (Notify).

  LongTermMemory (LTM) is an object that constitutes the long-term storage unit 56, and is used to hold information obtained by learning such as the name of an object for a long period of time. LongTermMemory, for example, can associatively store changes in internal state from external stimuli in a certain behavior module.

  The InternalStatusManager (ISM) is an object constituting the internal state management unit 54 and manages several types of emotions such as instinct and emotion by modeling them, and external stimuli (ES that are recognized by each object of the recognition system described above. : ExternalStimula) manages the internal state of the robot device 1 such as instinct and emotion.

  SituatedBehaviorsLayer (SBL) is an object constituting the situation-dependent behavior layer 58. SBL is an object that becomes a client (STM client) of ShorTermMemory, receives notification (Notify) of information about external stimuli (targets and events) periodically from ShorTermMemory, and schema (namely, behavior module to be executed) decide. Details of this SBL will be described later.

  The Reflexive SBL is an object that constitutes the reflex action unit 59, and performs reflexive and direct body motion according to the external stimulus recognized by each object of the recognition system described above. For example, the behavior of avoiding the detected obstacle is performed.

  As described above, SituatedBehaviorsLayer selects an action according to a situation such as an external stimulus or a change in an internal state. In contrast, Reflexive SBL acts reflexively in response to external stimuli. Since the behavior selection by these two objects is performed independently, when the behavior modules (schema) selected from each other are executed on the aircraft, the hardware resources of the robot 1 may compete and cannot be realized. is there. Therefore, an object called ResourceManager mediates hardware contention when selecting actions by SituatedBehaviorsLayer and Reflexive SBL. Then, the airframe is driven by notifying each object that realizes the airframe motion based on the arbitration result.

SoundPerformer, MotionController, and LEDController are objects that realize the aircraft motion. SoundPerformer is an object for outputting sound, performs sound synthesis in accordance with a text command given from SituatedBehaviorLayer via ResourceManager, and outputs sound from a speaker on the body of the robot 1. The MotionController is an object for performing the operations of the actuators A ₂ , A ₃ ... On the airframe, and is applicable in response to receiving a command to move a hand or a leg from the SituatedBehaviorLayer via the ResourceManager. Calculate the joint angle. The LEDController is an object for performing blinking operation of the LED (Light Emitting Diode), and performs blinking driving of the LED in response to receiving a command from the SituatedBehaviorLayer via the ResourceManager.

  FIG. 6 schematically shows the form of the situation-dependent action control by the situation-dependent action hierarchy (SBL) 58 (including the reflex action part 59) described above. The recognition result of the external environment by the recognition systems 51 to 53 is given to the situation dependent action hierarchy (SBL) 58 as an external stimulus. In addition, a change in the internal state according to the recognition result of the external environment by the recognition systems 51 to 53 is also given to the situation-dependent action hierarchy (SBL) 58. In the situation-dependent action hierarchy (SBL) 58, the situation can be determined according to an external stimulus or a change in the internal state, and action selection can be realized.

  By the way, the situation-dependent action hierarchy (SBL) 58 prepares a state machine for each action module, and classifies recognition results of external information input from the sensor depending on actions and situations before that. Behavior is expressed on the aircraft. The behavior module is described as a schema having a monitoring function for determining a situation according to an external stimulus or an internal state, and an action function for realizing a state transition (state machine) accompanying the execution of the behavior. FIG. 7 schematically shows how the situation-dependent action hierarchy (SBL) 58 is composed of a plurality of schemas.

  The situation-dependent action hierarchy (SBL) 58 (more precisely, the hierarchy that controls the normal situation-dependent action among the situation-dependent action hierarchy 58) is configured as a tree structure in which a plurality of schemas are hierarchically linked. In response to external stimuli and changes in the internal state, a more optimal schema is judged in an integrated manner and behavior control is performed. The tree includes a plurality of subtrees (or branches) such as a behavior model obtained by formulating an ethological situation-dependent behavior and a subtree for executing emotional expression.

  Here, as an action of the robot apparatus 1, an interaction with a human is assumed, and a tree of a situation-dependent action hierarchy (SBL) 58 is configured with reference to an action observed by an actual person.

Specifically, when a person wants to talk to someone else,
(A) Find a partner (target)
(B) approach that partner (target),
(C) Speak (converse) with the partner (target)
An example of configuring the tree of the situation-dependent action hierarchy (SBL) 58 so as to be able to realize these actions will be described with reference to FIG.

  As shown in FIG. 8, the situation-dependent action hierarchy (SBL) 58 includes an abstract action category starting from a root schema that receives a notification (Notify) of an external stimulus from the short-term memory unit (ShortTermMemory) 55. A schema is arranged for each hierarchy so as to go to a specific action category. That is, in the hierarchy immediately below the Root schema, schemas “SearchTarget (search for a target)”, “ApproachTarget (close to the target)”, and “Dialogue (interact)” are arranged. It becomes. Below the SearchTarget schema, schemas describing actions related to specific search actions such as “LookTo” and “LookFor” are arranged. Similarly, schemas describing actions related to actions that approach specific targets such as “Tracking” and “Approach” are arranged below the ApproachTarget schema, and “Tracking” and “Chat” are arranged below the Dialogue schema. Is a schema describing actions related to a specific dialogue action. Note that the same schema can be arranged in different sub-trees as in the Tracking schema in the figure.

  Here, each schema in the present embodiment has a function of expressing an action independently, and independence (Modularity) from other schemas is enhanced. For this reason, when designing a schema, you can focus only on the characteristics of the behavior you want to design, taking into account other requirements that may occur when actually working in the tree structure. There is no need. In practice, each schema has a focus as motion-related information, and when operating, it is possible to refer to, for example, an object or person in the environment as a specific target. Depending on the specific operation for each schema, there is minimal information necessary and sufficient for the schema to operate, and such information constitutes the focus described above. Note that each schema can have a different focus.

  Since each schema depends on information included in the focus, it is independent of other schemas and the tree structure in which the schema is arranged. However, as described later, each schema can express an action in cooperation with other schemas.

  For example, a Tracking schema that realizes tracking behavior tracks the position of a target or observes the path of movement of the target and turns the face (head) toward the target. When the target is a human in the environment, when the Tracking schema is executed, the robot apparatus 1 continuously swings the head unit 3 to the left and right according to the relative positional relationship between itself and the target, thereby Unit 3 always faces the target. Here, as a focus of the Tracking schema, a symbol for identifying a target recognized by the visual recognition function unit 51 of the behavior control system 50 can be used. For example, when the visual recognition function unit 51 associates ID information for each recognized object (thing or person) or detected event, the ID information can be used as a focus.

  FIG. 9 is a diagram in which focus information for each schema is added to the tree structure shown in FIG. In the example of FIG. 9, most schemas do not require focus information other than the ID information (target ID) about the target, for example, the person in the environment who is the partner of the conversation, and only the Dialogue schema and the Chat schema are used for the conversation. Focus information indicating the content (topic) is required. Here, the LookFor schema does not have a focus because it does not require a specific target. That is, the LookFor schema can be searched for any target in the environment.

Further, as can be seen from FIG. 9, there is no restriction due to interference between the information included in the focus. In other words, each target ID can correspond to a different target (object or person) in the environment. In the absence of coherence, the overall expressed behavior is a simple combination of actions according to each schema. For example, as shown in FIG. 10, if the subtree ApproachTarget behavior, Tracking schema and Approach schema lower (child) is, for example, where the different targets that target T ₁ and the target T ₂ and focus, the robot apparatus 1, As shown in FIG. 11, the user walks toward the target T ₂ while tracking the target T ₁ .

  By the way, in this embodiment, each schema has an interface for exchanging data and control signals with each other, and can be recombined into a tree structure for realizing complex behavior. Each schema can also have child schemas, ie other schemas for interacting with the rest of the structure. Hereinafter, such a schema is referred to as a parent schema or a hub schema.

The parent schema defines the connection pattern (control policy) of the child schema or controls the child schema to some extent. Conversely, the child schema only operates according to the connection pattern defined by the parent schema and operates independently of the parent schema, or operates under the control of the parent schema. This connection pattern information is stored in a storage means (not shown) of the parent schema. For example, each schema can exchange focus information via the interface. For example, when the ApproachTarget schema can control the Tracking schema, the ApproachTarget schema can set the focus of the Tracking schema. In this case, the parent schema monitors the focus of the child schema, and controls the operation of the child schema, for example, by setting the focus when requested. ApproachTarget schema is the parent schema, as the focus of Tracking schema and Approach schema is a child schema showing an example of setting the target T ₁ in FIG. 12.

  Here, as described above, each schema may be a terminal node, that is, a child schema, or may be a hub node, that is, a parent schema. The parent schema can define a connection pattern of the child schema. Therefore, in the following, this connection pattern will be described in detail.

  In the example of FIG. 7, there is a typical parent-child connection pattern, ie, an interaction pattern, for each subtree. Hereinafter, it demonstrates in order.

  First, the SearchTarget schema is a parent schema of the LookFor schema and the LookTo schema, and a subtree of the SearchTarget action is configured by these three schemas. The LookFor schema is a schema that performs a search action (behavior for searching for something), and visually searches for a human face, for example. This schema uses the head unit 3 of the robot apparatus 1 to scan the environment for a face. Of course, other targets such as an object may be searched. The LookTo schema is a schema that performs an action of turning around a sound (an action of looking at the direction of the sound). For example, when a voice is heard, the head unit 3 is directed to the direction of the voice. As described above, the LookFor schema and the LookTo schema are independent schemas and can execute operations independently of other schemas.

  On the other hand, in the SearchTarget action subtree, the SearchTarget schema uses the LookFor schema and the LookTo schema as child schemas in order to realize more complex actions. The child schemas operate independently of each other without any interference (control) from the parent schema (SearchTarget schema). In other words, when the subtree of the SearchTarget action is being executed, the robot apparatus 1 continuously swings the head left and right by the operation of the LookFor schema, and stops when the target person's face is detected. At the same time, the robot apparatus 1 turns its head in the direction of the voice when a voice is heard in the environment by the operation of the LookTo schema.

  In this way, the SearchTarget schema acts as a neutral hub schema rather than controlling the child schema. In this specification, such a connection pattern is referred to as an OR type pattern (OR policy). In this OR type pattern connection relationship, any child schema can perform operations at any time without any interaction from other schemas. FIG. 13 shows a subtree of the SearchTarget action in this case.

  In this embodiment, such a complex behavior compared to a simple behavior based on a single schema only defines the connection pattern of the child schema without recombining the schema to suit a specific situation. Can be realized.

  Next, the ApproachTarget schema is a parent schema of the Tracking schema and the Approach schema, and a subtree of the ApproachTarget action is configured by these three schemas. The Tracking schema tracks the position of the target or observes the path of its movement and turns the face (head) toward the target. The Approach schema is a schema for performing an action of walking toward a target, and walks toward a target person, for example, until the person in the environment is within a predetermined distance. As described above, the Tracking schema and the Approach schema are independent schemas and can execute operations independently of other schemas.

However, in the ApproachTarget action subtree, the ApproachTarget schema uses the Tracking schema and the Approach schema as child schemas to implement more complex actions. In particular, the ApproachTarget schema is
(A) All child schemas work together,
(B) Check the consistency of child schema behavior to ensure that all child schemas have the same focus, eg, the same target. In other words, when the subtree of the ActionTarget action is executed and the target is a person in the environment, for example, the robot apparatus 1 determines the relative positional relationship between itself and the target and the action of the person and the person by the operation of the Tracking schema. Accordingly, the head unit 3 is continuously swung left and right, so that the head unit 3 always faces the target. At the same time, the robot apparatus 1 walks toward the person by the action of the Approach schema.

  In this way, the ApproachTarget schema controls the child schema. In this specification, such a connection pattern is called an AND type pattern (AND policy). In the connection relationship of this AND type pattern, all child schemas execute operations in cooperation. A sub-tree of the ApproachTarget action in this case is shown in FIG.

  As described above, in the present embodiment, such a complicated behavior is compared with a simple behavior based on one schema, and the child schema is connected without recombining the schema to suit a specific situation. This can be realized simply by defining the pattern.

Also, in the ApproachTarget action subtree, all child schemas connected in an AND type pattern must have the same focus. ApproachTarget schema is the parent schema, as the focus of Tracking schema and Approach schema is a child schema showing an example of setting the target T ₂ in Figure 15. In this case, the robot apparatus 1, as shown in FIG. 16, performs an action to walk toward the target T ₂ while tracking the target T _2.

  Subsequently, the Dialogue schema is a parent schema of the Tracking schema and the Chat schema, and a subtree of Dialogue actions is constituted by these three schemas. The child schema connection relation in the Dialogue action subtree is an AND type pattern, which is the same as the above-described ApproachTarget action subtree, and thus detailed description thereof is omitted.

As described above, the specific example in the present embodiment imitates an action when a human wants to talk to someone else, and the action of the robot apparatus 1 is composed of subtrees of SearchTarget action, ApproachTarget action, and Dialogue action. is doing. It is necessary to have a certain connection pattern for this complicated behavior, that is, a connection pattern that is continuously executed. That is, in order to have a conversation, the person needs to be within a predetermined distance from the robot apparatus 1, and in order to be near the person, the robot apparatus 1 needs to approach the person. The person needs to be in the environment, and the robot apparatus 1 must search for the person. In other words, the overall behavior of talking to a person is
(A) Find a partner (target)
(B) approach that partner (target),
(C) Speak (converse) with the partner (target)
It is described as a series of simple actions. In this specification, such a connection pattern is called a SEQUENCE type pattern (SEQUENCE policy). FIG. 17 shows a tree structure of the entire action in this case. In this SEQUENCE type pattern, an action can be started from different time points according to the current situation. For example, when the person who is talking is already near the robot apparatus 1, the ApproachTarget action can be omitted.

  The connection patterns such as the OR type pattern, the AND type pattern, and the SEQUENCE type pattern described above are examples, and the present invention is not limited to this example.

  By the way, the same schema can be a terminal node in one tree structure and a hub node in another tree structure. The schema interface sends information such as data and control signals from the schema and automatically handles different situations.

  Each schema can be designed to detect child schemas, if any, and define a specific control pattern, or it can be designed as a “pure” terminal node. In the latter case, when a child schema is arranged, a default control pattern, such as an OR type pattern, is used.

  Specifically, taking a subtree of the ApproachTarget action as an example, how a terminal schema, for example, an Approach schema becomes a hub schema in a certain tree structure will be described. As described above, the Approach schema is a schema that performs an action of walking toward a target, and walks toward a target person until, for example, the person in the environment is within a predetermined distance. However, since such an action does not consider an obstacle on the route to the target, there is a possibility that the obstacle collides with the obstacle and cannot reach the target.

  Therefore, in order to improve the performance of the robot apparatus 1, a navigation schema for performing an action to avoid an obstacle can be provided. This Navigation schema is a schema that performs an action of navigating a direction, and shows an alternative route, for example, a route that bypasses an obstacle when an obstacle in the direction in which the robot device 1 travels is detected. This Navigation schema can be arranged as a child schema of the Approach schema, and there is no need to redesign the Approach schema. The Approach schema and the Navigation schema can operate in cooperation only by connecting the Navigation schema with the default control pattern, for example, the OR type pattern. FIG. 18 shows a sub-tree of ApproachTarget actions in this case. As a result, as shown in FIG. 19, the robot apparatus 1 tracks a specific person by the operation of the Tracking schema, and at the same time walks toward the person by the operation of the Approach schema. When the obstacle Ob is detected, the robot apparatus 1 bypasses the obstacle Ob, for example, using the navigation schema.

  As described above, the situation-dependent action hierarchy (SBL) 58 in this embodiment is configured as a tree structure in which a plurality of schemas are hierarchically connected, and the independence is enhanced so that each schema can execute its own action. Therefore, recombination of the tree structure is easy. At this time, the parent schema can define the connection pattern of the child schema, such as the above-mentioned OR type pattern, AND type pattern, and SEQUENCE type pattern, and can change the behavior pattern to be expressed.

  In addition, since the independence of each schema is enhanced, a new child schema can be added without rewriting the schema, whereby a new operation or function can be added to the robot apparatus.

Next, control of the child schema by the parent schema will be described in more detail with reference to the drawings.
As described above, the parent schema controls the child schema connected to itself based on the connection pattern stored in the storage means (not shown). However, the common information with the child schema (the execution request level AL and the resource By exchanging information), it is possible to control the start and end of the action according to the connection pattern. This control is basically as shown in FIG. That is, first, the child schemas S1, S2, S3 transmit to the parent schema S0 the execution requesting degree AL of their own actions and necessary resources calculated based on the external stimulus and the internal state, and the parent schema S0 receives this The information and its own information (execution request level AL and resource) are integrated and transmitted to the parent schema SP. Then, the parent schema SP transmits the execution rights and resources necessary for the action to the parent schema S0. The parent schema S0 removes the resources necessary for itself, and then transfers the remaining resources to the child schemas S1, S2, S3. To distribute. In this way, by exchanging common information, the parent schema can control the child schema without knowing the contents of the child schema.

  Specifically, first consider the case of an OR type pattern as shown in FIG. The SearchTarget schema shown in FIG. 21 is a parent schema of the LookFor schema, the LookTo schema, and the Utter schema, and the four schemas constitute a subtree of the SearchTarget action. The LookFor schema is a schema that performs a search action (behavior for searching for something), and visually searches for a human face, for example. This schema uses the head unit 3 of the robot apparatus 1 to scan the environment for a target. The LookTo schema is a schema that performs an action of turning around a sound (an action of looking at the direction of the sound). For example, when a voice is heard, the head unit 3 is directed to the direction of the voice. The Utter schema is a schema that emits a word (such as “Where?

  In the sub-tree shown in FIG. 21, the LookFor schema, LookTo schema, and Utter schema each transmit their own execution request level AL and resources (head unit, speaker, etc.) to the SearchTarget schema, and the SearchTarget schema stores information about them. Integrate and communicate to higher-level schema. When the execution right and resources are transmitted from the higher-level schema, the SearchTarget schema distributes them to the child schema.

  At this time, since the required resources of the LookFor schema and the LookTo schema are competing, the SearchTarget schema distributes the resources to the schema having a high execution request level AL out of the two schemas. For example, in a normal state, the execution request degree AL is larger in the LookFor schema than in the LookTo schema, so resources are distributed to the LookFor schema. As a result, the robot apparatus 1 performs a search action while speaking words. On the other hand, when something is uttered or a sound is heard, the LookTo schema has a higher execution request level AL than the LookFor schema, so resources are distributed to the LookTo schema. As a result, the robot apparatus 1 performs an action of turning around the sound while speaking a word.

In the OR type pattern shown above, it is not necessary to execute all of the LookFor schema, LookTo schema, and Utter schema at the same time.
(A) The SearchTarget schema can be started,
(B) The execution request level AL of at least one of the LookFor schema, the LookTo schema, and the Utter schema is greater than 0.
(C) Among the LookFor schema, the LookTo schema, and the Utter schema, the resource can be distributed to at least one schema of which the execution request level AL is greater than 0.

In addition, in the OR type pattern, any of the LookFor schema, LookTo schema, and Utter schema need only be executed.
(D) All of the SearchTarget schema, LookFor schema, LookTo schema, and Utter schema are terminated due to success or failure. Therefore, even if the target is lost during execution of the LookTo schema, the subtree is not terminated, and the action for searching for the target again by the LookFor schema is performed.

  Next, consider the case of an AND type pattern as shown in FIG. The ApproachTarget schema shown in FIG. 14 is a parent schema of the Tracking schema and the Approach schema, and a subtree of the ApproachTarget action is configured by these three schemas. The Tracking schema tracks the position of the target or observes the path of its movement and turns the face (head) toward the target. The Approach schema is a schema for performing an action of walking toward a target, and walks toward a target person, for example, until the person in the environment is within a predetermined distance.

  In the subtree shown in FIG. 14, the Tracking schema and the Approach schema each transmit their own execution request level AL and resources (head unit, leg unit, etc.) to the ApproachTarget schema. Integrate and communicate to higher-level schema. When the execution right and the resource are transmitted from the higher-level schema, the ApproachTarget schema distributes them to the Tracking schema and the Approach schema.

  At this time, since the Tracking schema and the Approach schema need to be executed at the same time, if any of the resources required for the Tracking schema and the Approach schema is insufficient, the resource is not transmitted from the higher-level schema to the ApproachTarget schema. .

In the AND type pattern shown above, since the Tracking schema and the Approach schema need to be executed at the same time, the sub-tree start condition is
(A) ApproachTarget schema can be started,
(B) Each of the execution request levels AL of the Tracking schema and the Approach schema is greater than 0,
(C) Resources can be distributed to each of the Tracking schema and the Approach schema.

In the AND type pattern, both the Tracking schema and the Approach schema need to be executed.
(D) At least one of the Tracking schema and the Approach schema is terminated due to success or failure. Accordingly, if the target cannot be further advanced due to an obstacle or the like, the Approach schema ends in failure, but in this case, the ApproachTarget schema also ends the Tracking schema.

  Here, in the above-mentioned OR type pattern and AND type pattern, each child schema was in a parallel relationship, but any one of the child schemas is the main schema, and the result of the entire subtree depends on this main schema. It does not matter if you make it. In this specification, such a connection pattern is called a DependOn type pattern (DependOn policy).

  Specifically, consider the case of the DependOn type pattern shown in FIG. The KickTarget schema shown in FIG. 22 is a parent schema of the Tracking schema and the Kick schema, and a subtree of KickTarget actions is configured by these three schemas. The Tracking schema tracks the position of a target or observes its path of movement and directs the entire body in the direction of the target. The Kick schema is a schema for performing an action of kicking a target, and kicks a target ball such as an environmental ball.

  In the subtree shown in FIG. 22, each of the Tracking schema and the Kick schema transmits its own execution request level AL and resources (head unit, leg unit, etc.) to the KickTarget schema. In addition, the Kick schema transmits information that it is the main schema to the KickTarget schema. The KickTarget schema integrates the information and transmits it to a higher-level schema. When execution rights and resources are transmitted from the higher-level schema, the KickTarget schema distributes them to the Tracking schema and the Kick schema.

  At this time, it is necessary to execute at least the Kick schema out of the Tracking schema and the Kick schema. Therefore, when the resources necessary for the Kick schema are insufficient, the resources are not transmitted from the higher-level schema to the KickTarget schema.

In the DependOn type pattern shown above, it is necessary to execute at least the Kick schema out of the Tracking schema and Kick schema, so the subtree start condition is
(A) The KickTarget schema can be started,
(B) Of the Tracking schema and Kick schema, at least the Kick schema execution request level AL is greater than 0,
(C) Of the Tracking schema and Kick schema, resources can be distributed to at least the Kick schema.

Also, in the DependOn type pattern, the result of the entire subtree depends on the Kick schema that is the main schema, so the subtree end condition is
(D) The KickTarget schema and the Kick schema are terminated due to success or failure. Therefore, if the kick kicks off the target and the Kick schema ends successfully, the KickTarget schema also ends the Tracking schema.

Then, taking soccer action as an example,
(A) Find the ball (target)
(B) Approach the ball (target),
(C) A tree structure of the entire action of kicking the ball (target) is shown in FIG. In FIG. 23, the Root schema takes a DependOn type pattern whose main schema is the KickTarget schema. Also, the KickTarget schema takes a DependOn type pattern with the Kick schema as the main schema, as in FIG.

  In the tree shown in FIG. 23, the search target schema sub-tree is used to search for a ball, and the ApproachTarget schema sub-tree approaches the ball until it reaches a predetermined distance. The ball is then kicked by the KickTarget schema subtree and the tree is terminated. Here, if the ball is found and the ball is lost while approaching the ball, the ApproachTarget schema ends in failure, but the KickTarget schema that is the main schema has not ended, so it does not end as a tree. In this case, the SearchTarget schema subtree is executed again, and the recovery action of searching for the ball can be performed.

  As described above, the situation-dependent action hierarchy (SBL) 58 in the present embodiment is configured as a tree structure in which a plurality of schemas are hierarchically connected, and can implement complex actions. Since the independence (modularity) is enhanced so that schemas can perform their own actions, the tree structure can be easily recombined, and common information can be exchanged between schemas. By specifying the connection relationship, the schema description can be simplified.

  In other words, it is difficult to describe all the information and functions necessary for controlling the child schema in the parent schema when the tree structure of the schema becomes complicated, especially for the schema that controls the child schema within the tree structure. There is a risk that there will be more than the number of child schemas.

  On the other hand, in this Embodiment mentioned above, the independence of a schema can be ensured by sharing the information to exchange, and the recombination of a unit (tree structure) can be made easy. Furthermore, the description of the schema can be simplified by extracting some common schemas and creating several connection patterns.

  It should be noted that the present invention is not limited to the above-described embodiments, and various modifications can be made without departing from the scope of the present invention.

  For example, in the above-described embodiment, a bipedal legged mobile robot has been described. However, the robot apparatus can be applied as long as it operates in accordance with the external environment and the internal state, and the moving means has two legs. It is not limited to walking or even legged movement.

  According to the present invention described above, among a plurality of behavior modules configured in a tree structure format, one or more behaviors in which a higher-order behavior module is connected to itself based on a control policy stored in a storage unit Since the modules are controlled, the independence of each behavior module can be increased. Therefore, it is possible to easily change the behavior design of the robot apparatus by recombining the tree structure of the behavior modules.

It is a perspective view which shows the external appearance structure of the robot apparatus in this Embodiment. It is a figure which shows typically the freedom degree structural model of the robot apparatus. It is a block diagram which shows the circuit structure of the robot apparatus. It is a figure which shows the basic architecture of the action control system of the robot apparatus. It is a figure which shows typically the object structure of the action control system. It is a figure which shows typically the form of the situation dependence action control by the situation dependence action hierarchy of the action control system. It is a figure which shows typically a mode that the same situation dependence action hierarchy is comprised by the some schema. It is a figure which shows typically the tree structure of the schema in the same situation dependence action hierarchy. It is a figure which shows a mode that the focus information for every schema was added to the tree structure. It is a figure which shows the subtree structure of the ApproachTarget action when a tracking schema and an Approach schema focus on different targets, respectively. It is a figure which shows typically the action of the robot apparatus when a tracking schema and an Approach schema each make a different target a focus. It is a figure which shows the subtree structure of ApproachTarget action when ApproachTarget schema sets the same focus with respect to Tracking schema and Approach schema. It is a figure which shows the subtree structure of SearchTarget action when a child schema is connected by OR type pattern. It is a figure which shows the subtree structure of ApproachTarget action when a child schema is connected by AND type pattern. It is a figure which shows the subtree structure of an ApproachTarget action when ApproachTarget schema sets the same focus with respect to a child schema. It is a figure which shows typically the action of a robot apparatus when ApproachTarget schema sets the same focus with respect to a child schema. It is a figure which shows a tree structure at the time of SearchTarget schema, ApproachTarget schema, and Dialogue schema being connected by the SEQUENCE type pattern. It is a figure which shows the subtree structure of the ApproachTarget action in case the Navigation schema is arrange | positioned under the Approach schema. It is a figure which shows typically the action of the robot apparatus when a Navigation schema is arrange | positioned under the Approach schema. It is a figure which shows the exchange of information between schemas. It is a figure which shows the subtree structure of SearchTarget action when a child schema is connected by OR type pattern. It is a figure which shows the subtree structure of ApproachTarget action when a child schema is connected by the DependOn type pattern. It is a figure which shows a tree structure at the time of SearchTarget schema, ApproachTarget schema, and KickTarget schema being connected by the DependOn type pattern.

Explanation of symbols

  DESCRIPTION OF SYMBOLS 1 Robot apparatus, 2 trunk unit, 3 head unit, 4R / L arm unit, 5R / L leg unit, 50 action control system, 51 visual recognition function part, 52 auditory recognition function part, 53 contact recognition function part , 54 internal state management unit, 55 short-term memory unit, 56 long-term memory unit, 57 contemplation behavior layer, 58 situation-dependent behavior layer, 59 reflex behavior unit, 60 hardware-dependent behavior control unit, 61 external environment

Claims (8)

In a robot apparatus having a movable part,
A movable part control means for controlling the movable part;
A behavior determination means configured in a tree structure format with a plurality of behavior modules as nodes ,
The behavior module includes a storage unit that stores a control policy that defines a connection pattern for uniquely executing one or more lower-level behavior modules connected to the behavior module.
The one or more lower-order behavior modules are necessary for the execution request level of the behavior of the one or more lower-order behavior modules calculated based on the external stimulus and the internal state and the execution of the one or more lower-order behavior modules themselves. Information related to the hardware resource of the robot apparatus is transmitted to a higher-order action module to which the one or more lower-order action modules are connected ;
The higher-order behavior module includes the information transmitted from the one or more lower-order behavior modules, the execution request level of the behavior of the higher-order behavior module itself, and the resources necessary for the execution of the higher-order behavior module itself, information about, on the basis of the above control policy, to one or more subordinate action module capable distribute the resources among the one or more subordinate behavior module, the said upper action module itself the resources required to perform Control to distribute the remaining resources ,
The movable unit control means, based on the level of the action module or the one or more subordinate behavior module has determined action, Carlo bots device controls the moving part. The higher-order behavior module distributes the remaining resources excluding resources necessary for the execution of the higher-order behavior module itself to the lower-order behavior module having a high execution request level among the one or more lower-order behavior modules. The robot apparatus according to claim 1, which is controlled as described above. Behavior module of the upper, of the one or more subordinate behavior module, when all the behavior modules is executable, 請 Motomeko 1 that controls so as to execute the one or more subordinate behavior module The robot apparatus described. Behavior module of the upper, of the one or more subordinate behavior module, when the execution of one action module finishes, the 請 Motomeko 1, wherein that control to stop the execution of other behavioral modules Robot device. In a behavior control method of a robot apparatus having a movable part,
The action determination means is configured in a tree structure format in which a plurality of action modules are included in a node and one or more lower-order action modules are connected to a higher-order action module.
The one or more lower-order behavior modules are required for the execution request level of the behavior of the one or more lower-order behavior modules calculated based on the external stimulus and the internal state and the execution of the one or more lower-order behavior modules themselves. Transmitting information about hardware resources of the robotic device to the higher-level action module;
The higher- level behavior module receives the information transmitted from the one or more lower-level behavior modules, the execution request level of the higher-level behavior module itself, and the resources necessary for the execution of the higher-level behavior module itself, information about, based on the control policy which defines the connection pattern for independently executing the stored the one or more subordinate behavior module in the storage means, the resources of the one or more subordinate behavior module the behavior module of one or more lower distributable, and controlling so as to distribute the remaining resources except for the resources needed to run the upper position of the action module itself,
Based on the above upper action module or the one or more subordinate behavior module has determined actions, actions control how having a and controlling the movable portion. The higher-order behavior module distributes the remaining resources excluding resources necessary for the execution of the higher-order behavior module itself to the lower-order behavior module having a high execution request level among the one or more lower-order behavior modules. The behavior control method according to claim 5, wherein control is performed as follows. Behavior module of the upper, of the one or more subordinate behavior module, when all the behavior modules is executable, 請 Motomeko 5 that controls so as to execute the one or more subordinate behavior module The behavior control method described. Behavior module of the upper, of the one or more subordinate behavior module, when the execution of one action module finishes, the 請 Motomeko 5, wherein that control to stop the execution of other behavioral modules Behavior control method.

Images