This teaching device comprises: a user interface unit capable of displaying a creation screen for a robot program; a teaching point display control unit for controlling displaying of previously taught teaching points on the creation screen; a teaching point selection unit for selecting a specific teaching point from the displayed teaching points; and a teaching point reuse unit for reusing the selected teaching point as a new teaching point for a robot program being created. The previously taught teaching points include at least one of a teaching point taught previously for the robot program being created and a teaching point taught previously for another robot program different from the robot program.

A method for planning a manipulation task of an agent, particularly a robot. The method includes: learning a number of manipulation skills wherein a symbolic abstraction of the respective manipulation skill is generated; determining a concatenated sequence of manipulation skills selected from the number of learned manipulation skills based on their symbolic abstraction so that a given goal specification indicating a given complex manipulation task is satisfied; and executing the sequence of manipulation skills.

This disclosure provides systems and methods for robotic task planning when a complex task instruction is provided in natural language. Conventionally robotic task planning relies on a single task or multiple independent or serialized tasks in the task instruction. Alternatively, constraints on space of linguistic variations, ambiguity and complexity of the language may be imposed. In the present disclosure, firstly dependencies between multiple tasks are identified. The tasks are then ordered such that a dependent task is always scheduled for planning after a task it is dependent upon. Moreover, repeated tasks are masked. Thus, resolving task dependencies and ordering dependencies, a complex instruction with multiple interdependent tasks in natural language facilitates generation of a viable task execution plan. Systems and methods of the present disclosure finds application in human-robot interactions.

A control device 1A mainly includes a display control means 15A and an operation sequence generation means 16A. The display control means 15A is configured to transmit display information S2 relating to a task to be executed by a robot to a display device 2A. The operation sequence generation means 16A is configured, in a case that the display control means 15A has received, from the display device 2A, task designation information that is input information which schematically specifies the task, to generate an operation sequence to be executed by the robot based on the task designation information Ia.

Robots are deployed for handling different tasks in various field of applications. For the robots to function, task planning is required to be done. During the task planning, goal setting is done, as well as actions to be executed for corresponding to each goal are decided. Traditionally, this is carried out first and then the robots start executing the task plan, thereby failing to capture any change in the environment the robots operate, post the task plan generation. Disclosed herein is a method and system for robotic task planning in which a task plan is generated and is executed. However if the task execution fails due to change in any of the parameters/factors, then the system dynamically invokes an adaptation and re-planning mechanism which either updates the already generated task plan (by capturing the change) or generates a new task plan, which the robot can execute to achieve the goal.

A control device 1C includes an operation sequence generation means 37C. The operation sequence generation means 37C is configured to generate, based on robot operation information Jr indicating operation characteristics of a robot executing a task and peripheral equipment information Ip indicating operation characteristics of peripheral equipment which delivers or receives an object relating to the task to or from the robot, operation sequences Sra and Spa indicating operations to be executed by the robot and the peripheral equipment, respectively.

The present disclosure relates to utilizing idle processing resources of a robot to reduce future burden on such processing resources. In particular, idle processing resources are utilized to identify future scenarios, and generate reactions to such future scenarios. The generated reactions are stored, and quickly retrieved as needed if corresponding identified future scenarios occur.

Provided is an operation command generation device including: an execution order determination unit configured to determine, based on respective arrangement positions of a plurality of process symbols each representing a process for a process subject on a protocol chart including the plurality of process symbols, an execution order of the plurality of process symbols; and a process symbol conversion unit configured to respectively convert the plurality of process symbols into jobs for a process system including at least a robot so that processes represented by the plurality of process symbols are executed in the execution order determined by the execution order determination unit.

Provided is an operation command generation device, which is configured to generate an operation command, which is a collection of jobs to fee performed by a process system of at least a robot, based on a protocol chart of at least a plurality of process symbols, the operation command generation device circuitry includes: a job generation unit configured to generate, based on the protocol chart, a job; apriority instruction unit configured to instruct a priority condition for determining a job execution order; and an execution order determination unit configured to determine an execution order of the jobs based on the priority instructed by the priority instruction unit by using a first condition about repeatedly execution of the jobs according to the number of the containers and a second condition about execution order of the jobs according to the arrangement of the process symbols in the protocol chart.

Provided is an operation command generation device configured to generate an operation command, which is a collection of jobs to be carried out by a process system including a robot based on a protocol chart including a process symbol representing a process to be carried out on a container containing a process subject, the operation command generation device including: a process job generation unit configured to generate, based on the process symbol, a job for causing the process system to carry out the process on the container at a work area; and a transfer job generation unit configured to generate, when the process represented by the process symbol is not a process to be carried out on the same container, a job to transfer the container from the work area to a retreat area after the process represented by the process symbol has been carried out.