Procedural memory learning and robot control
Methods and apparatus for procedural memory learning to control a robot by demonstrating a task action to the robot and having the robot learn the action according to a similarity matrix of correlated values, attributes, and parameters obtained from the robot as the robot performs the demonstrated action. Learning is done by an artificial neural network associated with the robot controller, so that the robot learns to perform the task associated with the similarity matrix. Extended similarity matrices can contain integrated and differentiated values of variables. Procedural memory learning reduces overhead in instructing robots to perform tasks. Continued learning improves performance and provides automatic compensation for changes in robot condition and environmental factors.
1. A method for procedural memory learning to control a robot to perform a task, the method comprising:
using a control system to:
compute a similarity matrix whose elements comprise values according to at least one function of similarity of a plurality of signals from the robot, the signals related to an action of the task performed by the robot with direct control command via a low-level interface;
input into an artificial neural network (ANN) controller of the robot:
the direct control command; and
the similarity matrix;
receive control signals from the ANN controller to control the robot;
aggregate the control signals from the ANN controller by an aggregator according to a kinematics model of the robot; and
send aggregated control signals from the aggregator to the robot, to perform the task.
2. The method of claim 1 , wherein the at least one function of similarity is selected from a group consisting of: correlation, cross-correlation, rank correlation, product-of-moments correlations, and distance correlation.
3. The method of claim 1 , wherein the values of the elements of the similarity matrix are complex numbers having real parts and imaginary parts.
4. The method of claim 3 , wherein the real parts and the imaginary parts are expressed as two separate matrices.
5. The method of claim 1 , wherein the similarity matrix is an extended similarity matrix whose values additionally include at least one moment selected from a group consisting of: an integrated value and a differentiated value.
6. The method of claim 1 , further comprising receiving additional control signals from an artificial neural network controller, and aggregating the additional control signals with the control signals by the aggregator.
7. An apparatus for procedural memory learning to control a robot to perform a task, the robot having a robot controller which includes an artificial neural network (ANN), the apparatus comprising:
a signal interface for receiving a plurality of signals from the robot controller;
a correlator for generating a correlation of at least two of the signals and producing a correlation output;
a matrix unit for generating a similarity matrix having an element containing the correlation and sending the matrix to the ANN via the robot controller;
a low-level control interface for sending direct control commands to the robot controller; and
an aggregator for aggregating control signals from the ANN according to a kinematics model of the robot.
8. The apparatus of claim 7 , further comprising a differentiator, for generating derivative values to extend the similarity matrix.
9. The apparatus of claim 7 , further comprising an integrator, for generating integrated values to extend the similarity matrix.
10. A computer-readable non-transitory storage medium including computer-executable instructions for procedural memory learning to control a robot to perform a task, which instructions, when executed by a computer, cause the computer to:
compute a similarity matrix whose elements comprise values according to at least one function of similarity of a plurality of signals from the robot, the signals related to an action of the task performed by the robot with direct control command via a low-level interface;
input into an artificial neural network (ANN) controller of the robot:
the direct control command; and
the similarity matrix;
receive control signals from the ANN controller to control the robot;
aggregate the control signals from the ANN controller by an aggregator according to a kinematics model of the robot; and
send-aggregated control signals from the aggregator to the robot, to perform the task.
11. The computer-readable non-transitory storage medium of claim 10 , wherein the at least one function of similarity is selected from a group consisting of: correlation, cross-correlation, rank correlation, product-of-moments correlations, and distance correlation.
12. The computer-readable non-transitory storage medium of claim 10 , wherein the similarity matrix is an extended similarity matrix whose values additionally include at least one moment selected from a group consisting of: an integrated value and a differentiated value.