Robot controller having function that simplifies learning, and robot control method
A robot controller having a function that simplifies learning and a robot control method. The robot controller includes: a learning section configured to carry out learning of detecting a deviation between a commanded trajectory representing a position of the robot generated according to the command values and an operation trajectory representing an actual position where the robot has moved, and generate a corrected program by adjusting the commanded trajectory; a saving section configured to save the corrected program; and a relearning section configured to carry out relearning on a relearning location, the relearning location being a part of the operation trajectory designated by an operator.
1. A robot controller configured to control operations of a robot in accordance with command values of a program, the controller comprising:
a processor configured to
carry out learning of detecting a deviation between (i) a commanded trajectory representing a position of the robot generated according to the command values and (ii) an operation trajectory representing an actual position where the robot has moved, and generate a corrected program by adjusting the commanded trajectory, and
carry out relearning on a relearning location, the relearning location being a part of the operation trajectory designated by an operator; and
at least one memory configured to
save the corrected program, and
save a learning result adopted by the operator.
2. The robot controller of claim 1 , wherein
the processor is configured to receive a designation of a method of the learning designated by the operator.
3. The robot controller of claim 1 , further comprising:
an operating screen configured to
display the operation trajectory after the learning, and
receive the relearning location designated by the operator.
4. The robot controller according to claim 1 , wherein
the robot is configured to accept accumulated statistical results of a judgment whether or not each learning result is adopted.
5. A robot control method of controlling operations of a robot in accordance with command values of a program, the method comprising:
carrying out learning of detecting a deviation between a commanded trajectory representing a position of the robot generated according to the command values and an operation trajectory representing an actual position where the robot has moved, and generating a corrected program by adjusting the commanded trajectory;
saving the corrected program;
carrying out relearning on a relearning location, the relearning location being a part of the operation trajectory designated by an operator; and
saving a learning result adopted by the operator.