Granted Patent B2

US 12,521,881 · App. 17/636,073 · Granted Jan 13, 2026

Inventor: Hiroyuki Oyama (Tokyo, JP)

Assignee: NEC CORPORATION

B25J9/1661B25J9/1697

Abstract

Claims (50)

1 . A control method executed by an information processing device, the control method comprising:

converting an objective task expressed in natural language, which is a task to be performed with respect to a target object existing in a workspace by a robot and indicates a final state of the target object, into a temporal logical formula using one or more operators and one or more propositions;

acquiring constraint condition information indicative of a constraint condition to be satisfied in performing the objective task;

generating a target logical formula obtained by adding a proposition indicative of the constraint condition to the logical formula by logical AND;

generating, based on the target logical formula, a time step sequence of sub-tasks each of which is a task in units of command that the robot can accept; and

controlling the robot in accordance with the time step sequence of the sub-tasks.

2 . A non-transitory computer readable storage medium storing a program executed by a computer, the program causing the computer to:

convert an objective task expressed in natural language, which is a task to be performed with respect to a target object existing in a workspace by a robot and indicates a final state of the target object, into a temporal logical formula using one or more operators and one or more propositions;

acquire constraint condition information indicative of a constraint condition to be satisfied in performing the objective task;

generate a target logical formula obtained by adding a proposition indicative of the constraint condition to the logical formula by logical AND;

generate, based on the target logical formula, a time step sequence of sub-tasks each of which is a task in units of command that the robot can accept; and

control the robot in accordance with the time step sequence of the sub-tasks.

3 . An information processing device comprising:

at least one memory configured to store instructions; and

at least one processor configured to execute the instructions to:

convert an objective task expressed in natural language, which is a task to be performed with respect to a target object existing in a workspace by a robot and indicates a final state of the target object, into a temporal logical formula using one or more operators and one or more propositions;

acquire constraint condition information indicative of a constraint condition to be satisfied in performing the objective task;

generate a target logical formula obtained by adding a proposition indicative of the constraint condition to the logical formula by logical AND;

generate, based on the target logical formula, a time step sequence of sub-tasks each of which is a task in units of command that the robot can accept; and

control the robot in accordance with the time step sequence of the sub-tasks.

4 . The information processing device according to claim 3 ,

wherein the at least one processor is further configured to recognize, on a basis of an output signal from measurement device, a type and a position of the target object as a measurement result in the workspace, and

set, on a basis of the measurement result, an abstract state of the target object as a proposition to be used in the target logical formula.

5 . The information processing device according to claim 4 ,

wherein the at least one processor is configured to recognize the object and an area existing in the workspace based on the measurement result and determines the proposition based on a recognition result relating to the object and the area and the constraint condition information.

6 . The information processing device according to claim 3 ,

wherein the at least one processor is configured to acquire the constraint condition information indicating the constraint condition corresponding to a type of the objective task.

7 . The information processing device according to claim 3 ,

wherein the at least one processor is further configured to receive an input for specifying a type of the objective task and a final state of a target object subjected to operation by the robot, and

wherein the at least one processor is configured to transmit a display signal of an input view for receiving the input to a display device.

8 . The information processing device according to claim 7 ,

wherein the at least one processor is configured to further receive an input relating to a prospective time to be required for performing the objective task.

9 . The information processing device according to claim 7 ,

wherein the at least one processor is configured to transmit, to the display device, a display signal for displaying, on a basis of the input, an animation in which the robot performs the objective task.

10 . The information processing device according to claim 3 ,

wherein the at least one processor is further configured to generate, from the target logical formula, a time step logical formula that is a logical formula indicative of a state for each time step to perform the objective task.

11 . The information processing device according to claim 10 ,

wherein the at least one processor is configured, in a case where a plurality of candidates exist as the logical formula indicative of the state for each time step, to generate the time step logical formula in which the candidates are combined by logical OR.

12 . The information processing device according to claim 11 ,

wherein the at least one processor is configured to acquire operation limit information regarding an operation limit of the robot, and excludes an unfeasible candidate, which is selected from the plurality of the candidates, from the time step logical formula based on the operation limit information.

13 . The information processing device according to claim 10 ,

wherein the at least one processor is further configured to generate, on a basis of the time step logical formula, a sequence of sub-tasks each of which is a task in units of command that the robot can accept.

14 . The information processing device according to claim 13 ,

wherein the at least one processor is further configured to generate an abstract model in which dynamics in a workspace where the robot works are abstracted; and

determine a control input for controlling the robot at each time step, based on the abstract model and the time step logical formula,

wherein the at least one processor is configured to generate the sequence of the sub-tasks based on the control input.

15 . The information processing device according to claim 3 ,

wherein the at least one processor is further configured to

receive an input for specifying a type of the objective task and the final state of the target object subjected to operation by the robot, and

perform the conversion based on the type of the objective task and the final state of the target object.

Assignments (1)

Continuity (1)

References Cited (28)

Cited By (1)

US 12,728,530