Reduced degree of freedom robotic controller apparatus and methods
Apparatus and methods for training and controlling of, for instance, robotic devices. In one implementation, a robot may be trained by a user using supervised learning. The user may be unable to control all degrees of freedom of the robot simultaneously. The user may interface to the robot via a control apparatus configured to select and operate a subset of the robot's complement of actuators. The robot may comprise an adaptive controller comprising a neuron network. The adaptive controller may be configured to generate actuator control commands based on the user input and output of the learning process. Training of the adaptive controller may comprise partial set training. The user may train the adaptive controller to operate first actuator subset. Subsequent to learning to operate the first subset, the adaptive controller may be trained to operate another subset of degrees of freedom based on user input via the control apparatus.
1. A user interface apparatus for use with a robotic apparatus comprising a controller, the user interface apparatus comprising:
a user input apparatus; and
first computerized logic in data communication with the input apparatus and configured to, as part of a first operational iteration, provide an input to the controller, the input associated with operation of one of first and second degrees of freedom of the robotic apparatus;
wherein the input is configured to enable the controller to produce,
a first control signal to control the first degree of freedom, the first control signal being determined based at least on an input being provided via the input apparatus;
a second control signal to control the second degree of freedom, the second control signal being determined based at least on another input being provided via the input apparatus, the another input being associated with the second degree of freedom, wherein the first and the second control signals are configured to cause the robotic apparatus to perform a target action;
an adjusted learning parameter based at least on a first performance relating to a first action and the target action; and
a third control signal based at least on the context and the adjusted learning parameter, which causes the robotic apparatus to execute a task during a subsequent operational iteration, wherein the task comprises operating the first degree of freedom in accordance with the third control signal and the second degree of freedom with the second control signal, the third control signal being produced subsequent to the first operational iteration.
2. The apparatus of claim 1 , further comprising switching logic, wherein the switching logic comprises one or more of: (i) a button, (ii) a switch, (iii) a timer, (iv) condition determination logic, (v) logic configured to determine a state of the robotic apparatus, (vi) performance measurement determination logic; and/or (vii) an audio indication detection logic.
3. The apparatus of claim 1 , wherein:
the first control signal is generated contemporaneous with provision of the input;
and the interface apparatus is selected from a group consisting of a joystick, a slider, a touch interface, and audio interface.
4. A method of training an adaptive controller apparatus of a robot, the robot comprising first and second degrees of freedom, the method comprising:
during a first operational iteration:
causing the apparatus to produce a first control signal based at least on a context and a first training input provided by a user, the first control signal being configured to operate the first degree of freedom to execute a first action; and
causing the apparatus to adjust a learning parameter based at least on a first performance relating to the first action and a target action; and
causing the apparatus to produce a second control signal based at least on the context and a second training input provided by the user, the second control signal being configured to operate the second degree of freedom; and
during a subsequent operational iteration initiated by a third input:
causing the apparatus to produce a third control signal based at least on the context and the adjusted learning parameter in absence of additional user input, the third control signal being configured to operate the first degree of freedom;
wherein the second and the third control signals cooperate to cause execution of the target action.
5. The method of claim 4 , wherein the first and the second training input are provided by a human trainer via a remote interface control element configured to control at least one of the first or the second degree of freedom at a given time.
6. The method of claim 5 , wherein the first control signal is determined based at least on a collaboration between the trainer and the adaptive controller, the collaboration characterized by a transfer function configured to combine the first training input and an output of the adaptive controller during the first iteration, the combination configured to produce the first control signal.
7. The method of claim 6 , wherein the combination is configured based on one or more of an additive operation and a union operation.
8. The method of claim 4 , wherein the target action execution is configured based at least on a contemporaneous operation of the first and the second degree of freedom at a given time.
9. The method of claim 4 , wherein the second training input is configured based at least on a state of the first degree of freedom.
10. The method of claim 9 , wherein the third input comprises a replay, during the second iteration, of the first training input provided and the second training input provided during the first iteration.
11. The method of claim 4 , wherein the third control signal is determined based at least on adaptation of the learning parameter configured to occur between the first and the second iteration.
12. A non-transitory computer readable storage medium having a plurality of instructions stored thereon which, when executed by a controller of a robot, causes the controller to:
during a first operational iteration:
produce a first control signal based at least on a context and a first training input provided by a user, the first control signal being configured to operate the first degree of freedom to execute a first action;
adjust a learning parameter based at least on a first performance relating to the first action and a target action; and
produce a second control signal based at least on the context and a second training input provided by the user, the second control signal being configured to operate the second degree of freedom; and
during a subsequent iteration:
produce a third control signal based at least on the context and the adjusted learning parameter in absence of additional user input, the third control signal being configured to operate the first degree of freedom;
wherein the second and the third control signals cooperate to cause execution of the target action.
13. The non-transitory computer readable storage medium of claim 12 , wherein,
the first and the second training input are provided by a human trainer via a remote interface control element configured to control at least one of the first or the second degree of freedom at a given time.
14. The non-transitory computer readable storage medium of claim 13 , wherein,
the first control signal is determined based at least on a collaboration between the trainer and the adaptive controller, the collaboration characterized by a transfer function configured to combine the first teaching input and an output of the adaptive controller during the first iteration, the combination configured to produce the first control signal.
15. The non-transitory computer readable storage medium of claim 14 , wherein,
the combination is configured based on one or more of an additive operation and a union operation.
16. The non-transitory computer readable storage medium of claim 12 , wherein,
the target action execution is configured based at least on a contemporaneous operation of the first and the second degree of freedom at a given time.
17. The non-transitory computer readable storage medium of claim 12 , wherein,
the second training input is configured based at least on the first degree of freedom state determined in accordance with the third control signal.
18. The non-transitory computer readable storage medium of claim 17 , wherein,
the third training input comprises a replay, during the second iteration, of the first training input provided during the first iteration.
19. The non-transitory computer readable storage medium of claim 12 , wherein,
the third control signal is determined based at least on based adaptation of the learning parameter configured to occur between the first and the second iteration.