KR20200071814A - Interaction System and Interaction Method for Human-Robot Interaction - Google Patents

Abstract

Provided is an interaction system for human-robot interaction. The interaction system for the human-robot interaction includes: a work command reception unit receiving a work command; a work command inference unit inferring the work command and determining at least one interaction type constituting the work command; and a robot motion command generation unit generating a robot motion command based on determined one or more interaction types and providing the generated robot motion command to a robot. The present invention provides the interaction system and method for the human-robot interaction which can support human-centered interaction for more efficient interaction between a human and the robot.

Description

Interaction System and Interaction Method for Human-Robot Interaction

The present invention relates to an interaction system and method for human-robot interaction (HRI), in an interface supporting human-robot interaction, an interaction system and method capable of supporting human-centered interaction It is about.

[Explanation on national support R&D]

This study is under the supervision of the Korea Research Foundation, "Study on Hand-based Seamless CoUI Technology Development for Remote User Collaboration" of the Global Frontier Support (R&D) Project of the Ministry of Science and ICT (Task ID: 1711073470, Detailed Assignment No. 2011-0031425).

With the development of robot technology, many things that humans have been doing in the industrial field are being replaced by robots, manipulators, etc., and humans are cooperating with robots, manipulators, or the industry is developing in the direction of controlling and managing them. . In addition, the number of cases in which robots are applied not only in the industrial field, but also in medical services, household services, and social services in which human interaction is important is increasing. Therefore, human-robot interaction becomes more important.

In order for the human-robot interaction to be efficiently performed, human-robot communication, that is, human commands must be naturally transmitted to the robot. However, since the language used by the human is different from the language used by the robot, inconvenience arises in that the human needs to provide detailed commands centered on the robot's operation in order to transmit commands to the robot. Exemplarily, the human wants the robot to perform the action "Put object A on object B", but considers the position, speed, acceleration, torque, and physical characteristics of the robot, and details of the robot that sets specific coordinates. Commands related to motion must be transmitted to the robot. That is, due to the gap between the somewhat abstract human language instructing the overall robot's work and the robot's language for the physical detailed motion of the robot, it is somewhat limited to effectively perform human-robot interaction. have.

Accordingly, there is a need for a system and method capable of supporting human-centered interaction for more efficient interaction between humans and robots.

M.R.Cutkosky, On Grasp Choice, Grasp Models, and the Design of Hands for Manufacturing Tasks, IEEE Trans. on Robotics and Automation, Vol. 5, No. 3, 1989

The present invention has been devised to solve the above-mentioned problems, and provides an interaction system and method for human-robot interaction capable of supporting human-centered interaction for more efficient interaction between humans and robots.

An interaction system for human-robot interaction according to an embodiment of the present specification includes a work command receiving unit for receiving a work command; A work command inference unit for inferring the work command and determining at least one interaction type constituting the work command; And a robot motion command generation unit that generates a robot motion command based on the determined one or more interaction types, and provides the generated robot motion command to a robot.

In one embodiment, the work command inference unit first classifies the work command into at least one sub-task, and classifies the classified at least one sub-task into the at least one interaction type, thereby classifying the work structure of the work command. Can decide.

In one embodiment, the interaction type generation interface, robot information, object information, further comprising a database unit including human information, the operation command inference unit read (Read-Out) the robot information from the database unit, The at least one interaction type may be determined by further considering the object information and the human information.

In one embodiment, the work command inference unit may determine the work structure of the work command by further considering the robot information, object information, and human information.

In one embodiment, the current object information, current robot information, and current human information reflecting the result of the robot's operation according to the robot operation command may be fed back and stored in the database unit.

In one embodiment, the robot motion command generation unit generates the robot motion command in consideration of the characteristics of the robot and the error caused by performing the interaction type, and changes the parameters applied to the interaction type appropriately, thereby allowing the current robot to It is possible to estimate whether the work order can be properly performed.

An interaction method for human-robot interaction according to another embodiment of the present invention includes receiving a work command; Determining at least one interaction type constituting the work command by inferring the work command; And generating a robot motion command based on the determined one or more interaction types, and providing the generated robot motion command to the robot.

In an embodiment, determining the at least one interaction type constituting the work command by inferring the work command may first classify the work command as at least one sub-task, and the classified at least one sub-task It may be classified into the at least one interaction type, and determining a work structure of the work command.

In one embodiment, the step of determining at least one interaction type constituting the work command by inferring the work command comprises reading an interaction type creation interface, robot information, object information, and human information from the database unit (Read -Out) and may further include determining the at least one interaction type by further considering the robot information, the object information, and the human information.

In one embodiment, the step of determining at least one interaction type constituting the work command by inferring the work command comprises reading an interaction type creation interface, robot information, object information, and human information from the database unit (Read -Out), and further considering the robot information, the object information, and the human information may include determining a work structure of the work command.

In one embodiment, after the operation of the robot is performed according to the provided robot operation command, the method may further include storing object information, robot information, and human information fed back to the database unit and stored.

In one embodiment, generating a robot motion command based on the determined one or more interaction types, and providing the generated robot motion command to the robot may include characteristics of the robot and errors generated by performing the interaction type. In consideration of the above, the robot operation command may be generated, and it may include estimating whether or not the current robot can properly perform a work command while appropriately changing parameters applied to the interaction type.

A storage medium according to another embodiment of the present invention is stored in a medium in combination with hardware to execute an interaction method for human-robot interaction according to any one of claims 7 to 12.

The interaction system and method for human-robot interaction according to an embodiment of the present invention may infer a work command, generate a command of an interaction type unit that is a minimum unit of interaction, and provide the command to the robot, and the robot is an interaction type unit Based on the command, the indicated operation is performed.

That is, since the command is transmitted in the minimum semantic unit of interaction between the human and the robot, it is possible to increase convenience for the human to instruct the work. In addition, as the interaction type unit, which is the minimum semantic unit of interaction, is used, the target of the corresponding task becomes clear and the robot can understand the entire task more easily, so that efficient human-centered interaction between human and robots is performed.

1 is an exemplary diagram for explaining an interaction system for human-robot interaction, and a relationship between humans and robots.
2 is a block diagram of an interaction system for human-robot interaction.
3 is a structural diagram showing a task structure of a task command.
4 is a flowchart of an interaction method for human-robot interaction according to an embodiment of the present invention.

For a detailed description of the present invention, which will be described later, reference is made to the accompanying drawings that illustrate, by way of example, specific embodiments in which the invention may be practiced. These embodiments are described in detail enough to enable a person skilled in the art to practice the present invention. Various embodiments of the present invention are different, but need not be mutually exclusive. For example, the specific shapes, structures, and properties described herein can be implemented in other embodiments without departing from the spirit and scope of the invention in connection with one embodiment. In addition, the location or placement of individual components within each disclosed embodiment can be changed without departing from the spirit and scope of the invention. Therefore, the detailed description to be described later is not described in a limiting sense, and the scope of the present invention is limited only by the appended claims, along with all ranges equivalent to the claims. In the drawings, similar reference numerals refer to the same or similar functions in various aspects.

The terminology used in the present specification is a general terminology that is currently widely used while considering functions, but this may vary according to intentions or customs of technicians in the field or the appearance of new technologies. In addition, in certain cases, some terms are arbitrarily selected by the applicant, and in this case, the meaning will be described in the description of the corresponding specification. Therefore, the terms used in this specification should be interpreted based on not only the names of simple terms, but the actual meanings of the terms and contents throughout the present specification.

1 is an exemplary diagram for explaining a relationship between an interaction system 10 for human-robot interaction, a human (H) and a robot (R).

Referring to FIG. 1, an interaction system for human-robot interaction may be a system for controlling the operation of the robot R according to a command of the human H. Here, the robot R may be a robot arm or a manipulator, but is not limited thereto, and may be a service robot that performs various services (medical service, housekeeping service, etc.) performed by a human as a robot having a human form. . The present invention provides a human-centered interaction system in which a human (H) and a robot (R) can interact more effectively and efficiently. That is, the human (H) can transmit the human-centered somewhat abstract work command to the robot R to the interaction system 10 for human-robot interaction, and the interaction system 10 for human-robot interaction By inferring this, a command suitable for the operation of the robot can be generated and provided to the robot. The interaction system for human-robot interaction of the present invention may be a system included in a robot, but is not limited thereto, and may be implemented as a system separate from the robot R. Hereinafter, the configuration and operation of the interaction system 10 for human-robot interaction according to the present embodiment will be described in more detail.

2 is a block diagram of an interaction system 10 for human-robot interaction. 3 is a structural diagram showing a task structure of a task command.

2 and 3, the interaction system 10 for human-robot interaction includes a work command receiving unit 110, a work command inference unit 120, a database unit 130, and a robot operation command generation unit ( 140).

The interaction system 10 for human-robot interaction according to embodiments and each device or unit constituting the same may have aspects that are entirely hardware, or partially hardware and partially software. For example, each component of the interaction system 10 for human-robot interaction refers to a combination of hardware and software driven by the hardware. The hardware may be a data processing device including a central processing unit (CPU) or other processor. Also, software driven by hardware may refer to a running process, an object, an executable, a thread of execution, a program, or the like. For example, the work command inference unit 120 may refer to a combination of hardware and software for inferring the work command.

In addition, each part constituting the interaction system 10 for human-robot interaction in the present specification is not intended to refer to separate components that are physically separated. That is, in FIG. 2, each part of the interaction system 10 for human-robot interaction is illustrated as a separate block that is distinct from each other, but this is related to the operation executed by the interaction system 10 for human-robot interaction. Functionally. Depending on the embodiment, some or all of the above-described parts may be integrated in the same one device, or one or more parts may be implemented as separate devices physically separated from other parts. For example, each part may be components communicatively connected to each other under a distributed computing environment.

The work command receiving unit 110 receives a work command. The work command may be a command to be performed by the robot. For example, it may not be a command that causes the robot to move to a specific coordinate, but rather a command for a rather abstract task such as delivering a specific object to a specific human. The command for the entire work to be performed by the robot may be a communication method that is more familiar to humans, and may be a human-centered interaction means, not a robot-centered one.

The work order may be a command provided by a human. The work command may be provided through an input means such as a keyboard and a mouse, but is not limited thereto, and may be generated by recognizing a human voice or a human action. The work command receiving unit 110 may include at least one of an input module to which a work command is input, a voice recognition module for recognizing human voice, and a motion recognition module for recognizing human motion. The work command received from the work command receiving unit 110 is provided to the work command inference unit 120.

The task command inference unit 120 infers a task command to determine a task tree. The work command is composed of at least one sub-task, and each sub-task is composed of at least one interaction type. The work command inference unit 120 determines at least one sub-task constituting the work command, and determines at least one interaction type required to perform the determined sub-task.

Illustratively, "pass object A to user 1"-a work command may consist of three sub-tasks: lifting object A, passing object A to user 1, and the home position (GoToHome). Object A lifting-sub operation may require three interaction types: MoveTo, Grasp, and LiftUp. The work command inference unit 120 determines a plurality of sub-tasks as described above and an interaction type required to perform each sub-task, after receiving a work command of “deliver object A to user 1”.

Here, in this embodiment, an interaction type such as MoveTo, Grasp, LiftUp may be a command of a minimum unit that causes an interaction between a human and a robot. The interaction system 10 for human-robot interaction can infer a work command and generate a command of an interaction type unit, which is a minimum unit of interaction, and provide it to the robot, and the robot works based on the interaction type unit command. Will do. That is, since the command is transmitted in the minimum semantic unit of interaction between the human and the robot, it is possible to increase convenience for the human to instruct the work. In addition, as the interaction type unit, which is the minimum semantic unit of interaction, is used, the target of the corresponding task becomes clear and the robot can understand the entire task more easily.

The interaction type may be a predefined state for natural interaction with the robot. Further, the detailed operation of the robot for the robot to perform the defined interaction may be a state defined according to each interaction type. This type of interaction can be created and added inside the system or outside the system. The interface of the interaction type is stored in the database unit 130, and the work command inference unit 120 dynamically adjusts an interaction type suitable for the current work command from the interaction type interface stored in the database unit 130 through inference. Can decide.

The database unit 130 may include an interaction type interface, robot information, object information, and human information. The information stored in the database unit 130 may be updated by reflecting the latest state of the robot, the object, the human, etc. after the robot executes the work command.

The robot information refers to information related to a robot performing a task, and at least includes information about the position of the robot. Here, the object is an object included in an environment to which a robot and a human belong, and means an object that can interact with a robot and/or a person. The object information includes physical information such as location information, size, and weight of all objects located in the environment. The human information refers to information about a human capable of interacting with the robot and the object, and includes at least human location information and a location (for example, a hand position) where the human interaction is performed.

The work command reasoning unit 120 may determine the work structure of the work command by further considering robot information, object information, and human information. That is, the work command inference unit 120 may further generate a sub task required to perform a work command in consideration of robot information, object information, and human information. As shown in FIG. 3, the work command provided from the work command receiving unit 110 is “delivering object A to user 1”, or considering object B information under which object A is located under object B. You can create additional subtasks to move. That is, the work command inference unit 120 considers information about a robot, an object, a human, and the like, and performs a sub-task for carrying out a work command to transfer the object A to the user 1 "lift object B, put object B down, object It can be decided by the configuration such as "A lifting, passing object A to user 1, home position (GoToHome)".

In addition, the work command inference unit 120 may dynamically determine (Dynamically) the type of interaction required to perform the sub-task by further considering robot information, object information, and human information stored in the database unit 130.

The interaction type may have different values set according to at least one of a work command, robot, human, and object information. In other words, the LiftUp operation of lifting object-sub operation and the LiftUp operation of lifting object B are composed of the same LiftUp interface, but the LiftUp operation lifting object A and LiftUp operation lifting object B are the details provided to the robot. There are differences in parameters.

As another example, even in an interaction type corresponding to the same MoveTo, the moving direction and speed may be different according to the object and the object. In addition, if there is an obstacle that is expected to collide in the movement process, the MovoTo must be generated to avoid the obstacle. In addition, when handing the object A to the user, the HandOver interaction type may be changed according to the location where the interaction with the human is performed. That is, depending on the work command and the surrounding environment, interaction types such as MoveTo and HandOver should be dynamically generated to have different parameter values. Accordingly, the work command inference unit 120 reads out an interface of information and an interaction type stored in the database unit 130 to a robot, an object, a human, and the like, and a plurality of interactions constituting a work command currently provided. Types can be created dynamically.

The work command inference unit 120 provides information on the dynamically generated interaction type through inference on the work command to the robot operation command generation unit 140.

The robot motion command generation unit 140 may determine a sequence of robot tasks so that the robot performs a plurality of dynamically generated interaction types, and generate a robot motion command. The robot motion command generation unit 140 may plan the motion of the robot based on the dynamically generated interaction type, and can overall plan the process in which each interaction type is performed. The robot motion command generation unit 140 may provide the generated robot motion command to the robot.

In addition, the robot motion command generation unit 140 may generate a robot motion command to be provided to the robot in consideration of an error generated as the robot performs characteristics and interaction types. That is, the robot motion command generation unit 140 may estimate the motion of the robot according to the generated robot motion command. The robot motion command generation unit 140 can estimate whether the current robot can properly perform a work command while appropriately changing parameters applied to each interaction type unit. The interaction system 10 for human-robot interaction according to the present embodiment generates a robot operation command in an interaction type unit, so that the estimated logic configuration can be united and the number of parameters can be minimized.

According to the robot motion command, which is a combination of interaction types, the robot can perform the entire operation, and the current information of the object, human, and robot reflecting the result of the robot's operation can be fed back and stored in the database unit 130. It can be used to dynamically create an interaction type corresponding to the next work command.

Hereinafter, an interaction method for human-robot interaction according to another embodiment of the present invention will be described.

4 is a flowchart of an interaction method for human-robot interaction according to an embodiment of the present invention. The method of interaction for human-robot interaction may be referred to the description of FIG. 2 as a method performed in the interaction system for human-robot interaction according to FIG. 2.

Referring to FIG. 4, an interaction method for human-robot interaction includes receiving a work command (S100), inferring a work command, and determining at least one interaction type constituting the work command (S110), and And generating a robot motion command based on the determined one or more interaction types, and providing the generated robot motion command to the robot (S120).

First, a work command is received (S100).

Receiving a work command may be performed by the work command receiving unit 110. The work order may be a command provided by a human. The work command may be provided through an input means such as a keyboard or a mouse, but is not limited thereto, and may be generated and provided by recognizing a human voice or a human action.

Subsequently, at least one interaction type constituting the work command is determined by inferring the work command (S110 ).

The step of determining the work structure by inferring the work command may be performed by the work command reasoning unit 120. The work command is composed of at least one sub-task, and each sub-task is composed of at least one interaction type. The work command inference unit 120 determines at least one sub-task constituting the work command, and determines at least one interaction type required to perform the determined sub-task. The interaction type may be a minimum unit command that causes human-robot interaction to occur. The interaction type may be a predefined state for natural interaction with the robot. That is, the interface of the interaction type is stored in the database unit 130, and the work command inference unit 120 infers an interaction type suitable for the current work command from among the interaction type interfaces stored in the database unit 130. Can be determined dynamically.

Determining at least one interaction type constituting the work command by inferring the work command (S110), reading the interaction type creation interface, robot information, object information and human information from the database unit (Read-Out) ), and further consider the robot information, the object information, and the human information to determine a work structure of the work command.

In addition, the step of determining at least one interaction type constituting the work command by inferring the work command (S110), reading the interaction type creation interface, robot information, object information and human information in the database unit (Read -Out), and determining the at least one interaction type by further considering the robot information, the object information, and the human information.

Next, a robot motion command is generated based on the determined one or more interaction types, and the generated robot motion command is provided to the robot (S120).

A robot operation order may be determined and a robot operation command may be generated so that the robot performs a plurality of dynamically generated interaction types. These steps are performed by the robot operation command generation unit 140. The robot motion command generation unit 140 may plan the motion of the robot based on the dynamically generated interaction type, and can overall plan the process in which each interaction type is performed. The robot motion command generation unit 140 may provide the generated robot motion command to the robot.

In addition, generating a robot operation command based on the determined one or more interaction types, and providing the generated robot operation command to the robot (S120), the characteristics of the robot, an error caused by performing the interaction type In consideration of the above, the robot operation command may be generated, and it may include estimating whether or not the current robot can properly perform a work command while appropriately changing parameters applied to the interaction type.

In the interaction method for human-robot interaction according to the present embodiment, after the operation of the robot is performed according to the provided robot operation command, object information, robot information, and human information are fed back and stored in the database unit. It may further include.

That is, according to the robot operation command, the robot can perform the entire operation, and the current information of the object, human, and robot reflecting the result of the robot's operation can be fed back to the database unit 130 and stored. Next It can be used to dynamically create an interaction type corresponding to a work order.

The operation by the interaction method for human-robot interaction according to the above-described embodiments may be recorded in a computer-readable recording medium at least partially implemented by a computer program. A program for implementing an operation by an interaction method for human-robot interaction according to embodiments is recorded, and a computer-readable recording medium includes all kinds of recording devices in which data that can be read by a computer is stored. do. Examples of computer-readable recording media include ROM, RAM, CD-ROM, magnetic tape, floppy disks, and optical data storage devices. In addition, the computer readable recording medium may be distributed over network coupled computer systems so that the computer readable code is stored and executed in a distributed manner. In addition, functional programs, codes, and code segments for implementing the present embodiment will be easily understood by those skilled in the art to which this embodiment belongs.

Although described above with reference to embodiments, the present invention should not be construed as being limited by these embodiments or the drawings, and those skilled in the art will think and scope of the present invention described in the following claims It will be understood that various modifications and changes can be made to the present invention without departing from the scope.

10: Interaction system for human-robot interaction
110: work command receiver
120: work order reasoning
130: database unit
140: robot operation command generation unit

Claims (13)

A work command receiver for receiving a work command;
A work command inference unit for inferring the work command and determining at least one interaction type constituting the work command; And
And a robot motion command generator for generating a robot motion command based on the determined one or more interaction types and providing the generated robot motion command to a robot. According to claim 1,
The work command inference unit may classify the work command into at least one sub-task first, and classify the classified at least one sub-task into the at least one interaction type to determine a work structure of the work command. Interaction system for human-robot interaction. According to claim 2,
It further includes a database unit including an interaction type creation interface, robot information, object information, and human information,
The operation command inference unit determines the at least one interaction type by further considering the robot information, the object information, and the human information read-out from the database unit. Interaction system for. According to claim 3,
The work command inference unit is an interaction system for human-robot interaction, characterized by determining the work structure of the work command in consideration of the robot information, object information, and human information. According to claim 3,
Interaction system for human-robot interaction, characterized in that current object information, current robot information, and current human information reflecting the result of the robot's operation according to the robot operation command are fed back and stored in the database unit. According to claim 1,
The robot motion command generation unit generates the robot motion command in consideration of the characteristics of the robot and the error generated by performing the interaction type
Interaction system for human-robot interaction, characterized by estimating whether a current robot can properly perform a work command while appropriately changing a parameter applied to the interaction type. Receiving a work order;
Determining at least one interaction type constituting the work command by inferring the work command; And
And generating a robot motion command based on the determined one or more interaction types, and providing the generated robot motion command to a robot. The method of claim 7,
Inferring the work command to determine at least one interaction type constituting the work command,
Human-robot interaction comprising first classifying the work order into at least one sub-work, and classifying the classified at least one sub-work into the at least one interaction type to determine a work structure of the work command. How to interact. The method of claim 8,
Inferring the work command to determine at least one interaction type constituting the work command,
The database unit reads out an interaction type creation interface, robot information, object information, and human information, and further determines the at least one interaction type by further considering the robot information, the object information, and the human information An interaction method for human-robot interaction, including doing. The method of claim 8,
Determining at least one interaction type constituting the work command by inferring the work command,
The database unit reads out an interaction-type creation interface, robot information, object information, and human information, and further considers the robot information, the object information, and the human information to determine a work structure of the work command. Including interaction method for human-robot interaction. The method of claim 8,
After the operation of the robot is performed according to the provided robot operation command, the object information, robot information, human information further comprises the step of being fed back and stored in the database unit interaction method for human-robot interaction. The method of claim 7,
Generating a robot motion command based on the determined one or more interaction types, and providing the generated robot motion command to the robot,
The robot operation command is generated in consideration of the characteristics of the robot and the error caused by performing the interaction type. A method of interaction for human-robot interaction, including estimating about a. A computer program stored in a medium to execute an interaction method for human-robot interaction according to any one of claims 7 to 12 in combination with hardware.

Images