Surgical robot system and control method thereof

1. A control method of a robot system, the control method comprising:

acquiring data regarding a motion of a master manipulator by an operator;

reading, from a database, results of learning a plurality of motions constituting different ones of a plurality of tasks, the learning the plurality of motions being performed offline prior to the motion of the master manipulator by the operator;

predicting which of the plurality of tasks is an executed task being performed by the operator and connecting the plurality of motions in a sequence associated with the executed task based on the acquired motion data and the results of learning the plurality of motions; and

adjusting a tool so as to correspond to the executed task such that the tool is controlled based on the sequence associated with the executed task.

2. The control method according to claim 1 , wherein the data regarding the motion of the master manipulator includes at least one of interactive force data between the master manipulator and the operator, position data of the master manipulator, and speed data of the master manipulator.

3. The control method according to claim 1 , wherein the executed task includes one or more of suturing, passing, running, and cannulation.

4. The control method according to claim 1 , wherein the plurality of motions associated with the executed task includes one or more of orient, push, and pull motions.

5. The control method according to claim 1 , wherein the learning of the plurality of motions is performed via machine learning.

6. The control method according to claim 5 , wherein the machine learning comprises:

supervised learning in which the data regarding the motion of the master manipulator is acquired beforehand and is an input, and learning is performed in a state in which a target value for the input is known.

7. A robot system, comprising:

a slave robot having a robot arm to which at least one tool is coupled; and

a master robot to control the slave robot, the master robot including,

a master manipulator configured to manipulate the robot arm;

a motion data detector configured to detect data regarding a motion of the master manipulator by an operator; and

a controller configured to,

read, from a database, results of learning a plurality of motions constituting different ones of a plurality of tasks, the learning the plurality of motions being performed offline prior to the motion of the master manipulator by the operator,

predict which of the plurality of tasks is an executed task being performed by the operator and connecting the plurality of motions in a sequence associated with the executed task based on the motion data detected via the motion data detector and the results of learning the plurality of motions constituting the executed task, and

control the at least one tool so as to correspond to the executed task such that the tool is controlled based on the sequence associated with the executed task.

8. The system according to claim 7 , wherein the motion data detector includes at least one of a force/torque sensor configured to detect interactive force data between the master manipulator and the operator, a position sensor configured to detect a position of the master manipulator, and a speed sensor configured to detect a speed of the master manipulator.

9. The system according to claim 7 , wherein the task includes one or more of suturing, passing, running, and cannulation.

10. The system according to claim 7 , wherein the plurality of motions constituting the task includes one or more of orient, push, and pull motions.

11. The system according to claim 7 , wherein the controller includes:

a first control signal generator configured to generate a first control signal to control a motion of the slave robot based on the data regarding the motion of the master manipulator acquired via the motion data detector;

a learner configured to learn the plurality of motions constituting the task based on previously acquired data regarding the motion of the master manipulator;

a predictor configured to predict the operator basic motion or the task based on the motion data detected via the motion data detector and the results of learning performed via the learner;

a second control signal generator configured to generate a second control signal to control the motion of the slave robot and/or the master manipulator having a redundant degree of freedom (DOF) based on the predicted basic motion or task; and

an image processor configured to process an image input from an endoscope coupled to the robot arm, and to output a picture image.

12. The system according to claim 7 , further comprising:

a storage configured to store, in the database, the results of learning the plurality of motions constituting the task acquired via the learner, and a reference image including at least one of an X-ray image, a Computed Tomography (CT) image, and a Magnetic Resonance Imaging (MRI) image.

13. The system according to claim 7 , further comprising:

a display unit configured to display an endoscopic image corresponding to an image signal provided from an endoscope coupled to the robot arm.

14. The control method according to claim 1 , further comprising:

selectively providing image data suitable for the predicted basic motion, or controlling zoom by changing a focal length of a zoom lens of a camera provided in an endoscope that is one kind of the tool.