Hierarchical robotic controller apparatus and methods

Abstract

A robot may be trained by a user guiding the robot along target trajectory using a control signal. A robot may comprise an adaptive controller. The controller may be configured to generate control commands based on the user guidance, sensory input and a performance measure. A user may interface to the robot via an adaptively configured remote controller. The remote controller may comprise a mobile device, configured by the user in accordance with phenotype and/or operational configuration of the robot. The remote controller may detect changes in the robot phenotype and/or operational configuration. The remote controller may comprise multiple control elements configured to activate respective portions of the robot platform. Based on training, the remote controller may configure composite controls configured based two or more of control elements. Activation of a composite control may enable the robot to perform a task.

1 .- 23 . (canceled) 
     
     
         24 . A system for controlling behavior of a robot based on adaptive learning, comprising:
 a memory having computer readable instructions stored thereon; and   at least one processor configured to execute the computer readable instructions to:
 associate a first weight to a first action outputted by a first sensor of a plurality of sensors on the robot; 
 adjust the first weight by associating a first value to the first weight if a teaching input signal is received from a user prior to the generation of the first action by the first sensor; and 
 adjust the first weight by associating a second value to the first weight if the teaching input signal is not received by the at least one processor prior to the generation of the first action, the second value being lower than the first value. 
   
     
     
         25 . The system of  claim 24 , wherein the at least one processor is further configured to execute the computer readable instructions to transmit a signal to the first sensor to initiate the first action in a subsequent phase if the first weight is associated the first value. 
     
     
         26 . The system of  claim 24 , wherein the at least one processor is further configured to execute the computer readable instructions to store a plurality of weights in the memory, wherein each one of the plurality of weights corresponds to a respective action outputted by the first sensor. 
     
     
         27 . The system of  claim 24 , wherein the at least one processor is further configured to execute the computer readable instructions to update a plurality of weights stored in the memory upon receiving the teaching signal from the user. 
     
     
         28 . The system of  claim 24 , wherein the at least one processor is further configured to execute the computer readable instructions to associate a second weight to a second action outputted by a second sensor of the plurality of sensors, wherein the first action corresponds to a first task and the second action corresponds to a subsequent task. 
     
     
         29 . The system of  claim 28 , wherein value of the first weight is greater than value of the second weight, and wherein the first task corresponds to avoiding obstacle along a path of the robot, and the second task corresponds to the robot moving along the path. 
     
     
         30 . The system of  claim 24 , wherein the at least one processor is further configured to execute the computer readable instructions to update at least one of a plurality of weights stored in memory by replacing a previous value corresponding to a respective one of the plurality of weights with a new value corresponding to another one of the plurality of weights based on the teaching input signal by the user. 
     
     
         31 . A method for controlling behavior of a robot based on adaptive learning, comprising:
 associating a first weight to a first action outputted by a first sensor of a plurality of sensors on the robot;   adjusting the first weight by associating a first value to the first weight if a teaching input signal is received from a user prior to the generation of the first action by the first sensor; and   adjusting the first weight by associating a second value to the first weight if the teaching input signal is not received by the at least one processor prior to the generation of the first action, the second value being lower than the first value.   
     
     
         32 . The method of  claim 31 , further comprising:
 transmitting a signal to the first sensor to initiate the first action in a subsequent phase if the first weight is associated the first value.   
     
     
         33 . The system of  claim 31 , further comprising:
 storing a plurality of weights in the memory, wherein each one of the plurality of weights corresponds to a respective action outputted by the first sensor.   
     
     
         34 . The method of  claim 31 , further comprising:
 updating a plurality of weights stored in the memory upon receiving the teaching signal from the user.   
     
     
         35 . The method of  claim 31 , further comprising:
 associating a second weight to a second action outputted by a second sensor of the plurality of sensors, wherein the first action corresponds to a first task and the second action corresponds to a subsequent task.   
     
     
         36 . The method of  claim 35 , wherein value of the first weight is greater than value of the second weight, and wherein the first task corresponds to avoiding obstacle along a path of the robot, and the second task corresponds to the robot moving along the path. 
     
     
         37 . The method of  claim 31 , further comprising:
 updating at least one of a plurality of weights stored in memory by replacing a previous value corresponding to a respective one of the plurality of weights with a new value corresponding to another one of the plurality of weights based on the teaching input signal by the user.   
     
     
         38 . A non-transitory computer readable medium having computer readable instructions stored that when executed by at least one processor cause the at least one processor to:
 associate a first weight to a first action outputted by a first sensor of a plurality of sensors on a robot;   adjust the first weight by associating a first value to the first weight if a teaching input signal is received from a user prior to the generation of the first action by the first sensor; and   adjust the first weight by associating a second value to the first weight if the teaching input signal is not received by the at least one processor prior to the generation of the first action, the second value being lower than the first value.   
     
     
         39 . The non-transitory computer readable medium of  claim 38 , wherein the at least one processor is further configured to execute the computer readable instructions to transmit a signal to the first sensor to initiate the first action in a subsequent phase if the first weight is associated the first value. 
     
     
         40 . The non-transitory computer readable medium of  claim 38 , wherein the at least one processor is further configured to execute the computer readable instructions to store a plurality of weights in the memory, wherein each one of the plurality of weights corresponds to a respective action outputted by the first sensor. 
     
     
         41 . The non-transitory computer readable medium of  claim 38 , wherein the at least one processor is further configured to execute the computer readable instructions to update a plurality of weights stored in the memory upon receiving the teaching signal from the user. 
     
     
         42 . The non-transitory computer readable medium of  claim 38 , wherein the at least one processor is further configured to execute the computer readable instructions to associate a second weight to a second action outputted by a second sensor of the plurality of sensors, wherein the first action corresponds to a first task and the second action corresponds to a subsequent task. 
     
     
         43 . The non-transitory computer readable medium of  claim 42 , wherein value of the first weight is greater than value of the second weight, and wherein the first task corresponds to avoiding obstacle along a path of the robot, and the second task corresponds to the robot moving along the path.