Feature detection apparatus and methods for training of robotic navigation

Abstract

A robotic device may be operated by a learning controller comprising a feature learning configured to determine control signal based on sensory input. An input may be analyzed in order to determine occurrence of one or more features. Features in the input may be associated with the control signal during online supervised training. During training, learning process may be adapted based on training input and the predicted output. A combination of the predicted and the target output may be provided to a robotic device to execute a task. Feature determination may comprise online adaptation of input, sparse encoding transformations. Computations related to learning process adaptation and feature detection may be performed on board by the robotic device in real time thereby enabling autonomous navigation by trained robots.

1 .- 22 . (canceled) 
     
     
         23 . A method of operating a robotic device by a controller, the method comprising:
 during an operation of a plurality of operations:
 causing, in a teacher-assisted trial, the robotic device to execute an action along a first trajectory in accordance with a first control signal determined based on a sensory input; 
 learning a first interrelationship between the sensory input and a state of the controller based at least in part on the teacher-assisted trial; 
 conveying information related to the first interrelationship to the controller; 
 updating one or more parameters of the controller in accordance with the information; and 
 during a subsequent operation of the plurality of operations:
 causing the robotic device to execute the action along a second trajectory in accordance with a second control signal determined based at least in part on the sensory input, and the execution of the action along the second trajectory is characterized by a second interrelationship; and 
 displacing the second trajectory closer the first trajectory based at least in part on the updated one or more parameters of the controller. 
 
   
     
     
         24 . The method of  claim 23 , wherein:
 the information includes a performance measure comprising a distance between the first trajectory and a target trajectory.   
     
     
         25 . The method of  claim 24 , wherein:
 the performance measure comprises a first probability parameter between the first trajectory and the target trajectory.   
     
     
         26 . The method of  claim 23 , wherein:
 the controller is configured for operation in accordance with a supervised learning process configured based on a teaching signal; and   the first control signal comprises a combination of a second layer output and a teaching signal provided to the robotic device.   
     
     
         27 . The method of  claim 23 , wherein:
 the operation and another operation occur at a part of an online learning process wherein within a given time period, the robot may receive a teaching input, modify the learning process based on the teaching input and the learning process configuration, and subsequently navigate a trajectory based on the modified learning process.   
     
     
         28 . The method of  claim 23 , wherein the learning the first interrelationship comprises a feature detection process. 
     
     
         29 . The method of  claim 23 , wherein the second trajectory varies from the first trajectory due at least in part to an obstacle along the first trajectory. 
     
     
         30 . The method of  claim 23 , wherein the teacher-assisted trial comprises demonstration of a target trajectory. 
     
     
         31 . A robotic device comprising:
 a platform comprising a motor;   a sensor;   a controller configured to:
 cause, in a teacher-assisted trial, the robotic device to execute an action utilizing the motor to navigate the platform along a first trajectory in accordance with a first control signal determined based on a sensory input from the sensor; 
 learn a first interrelationship between the sensory input and a state of the controller based at least in part on the teacher-assisted trial; 
 convey information related to the first interrelationship to the controller; 
 update one or more parameters of the controller in accordance with the information; and 
 during a subsequent operation of the plurality of operations:
 cause the robotic device to execute the action along a second trajectory in accordance with a second control signal determined based at least in part on the sensory input, and the execution of the action along the second trajectory is characterized by a second interrelationship; and 
 displace the second trajectory closer the first trajectory based at least in part on the updated one or more parameters of the controller. 
 
   
     
     
         32 . The apparatus of  claim 31 , further comprising a communications interface configured to receive an external input indicative of a target trajectory. 
     
     
         33 . The apparatus of  claim 32 , wherein:
 the external input comprises a training control indication;   the controller is further configured to operate a combiner process configured to produce a combined control indication based on the control indication and a teaching signal; and   provision of the combined control indication is configured to generate motor commands to execute the action.   
     
     
         34 . The apparatus of  claim 33 , wherein the combiner process is characterized by an override transfer function wherein a non-zero value of the training control indication is configured to cause determination of the combined control indication independent from the control indication. 
     
     
         35 . The apparatus of  claim 33 , wherein the combiner process is characterized by an additive transfer function. 
     
     
         36 . The apparatus of  claim 31 , wherein the controller is configured for operation in accordance with a supervised learning process configured based on a teaching signal; and 
     
     
         37 . The apparatus of  claim 31 , wherein the sensor is configured to obtain a plurality of video frames at a frame rate. 
     
     
         38 . The apparatus of  claim 37 , wherein the learning the first interrelationship comprises a feature detection process. 
     
     
         39 . A non-transitory computer-readable storage medium having a plurality of instructions stored thereon, the instructions being executable by a processing apparatus for navigating a robotic device, the instructions configured to, when executed by the processing apparatus, cause the processing apparatus to:
 cause, in a teacher-assisted trial, the robotic device to execute an action along a first trajectory in accordance with a first control signal determined based on a sensory input;   learn a first interrelationship between the sensory input and a state of the controller based at least in part on the teacher-assisted trial;   convey information related to the first interrelationship to the controller;   update one or more parameters of the controller in accordance with the information; and   during a subsequent operation of the plurality of operations:
 cause the robotic device to execute the action along a second trajectory in accordance with a second control signal determined based at least in part on the sensory input, and the execution of the action along the second trajectory is characterized by a second interrelationship; and 
 displace the second trajectory closer the first trajectory based at least in part on the updated one or more parameters of the controller. 
   
     
     
         40 . The non-transitory computer-readable storage medium of  claim 39 , wherein the teacher-assisted trial comprises demonstration of a target trajectory. 
     
     
         41 . The non-transitory computer-readable storage medium of  claim 39 , wherein the second trajectory varies from the first trajectory due at least in part to an obstacle along the first trajectory. 
     
     
         42 . The non-transitory computer-readable storage medium of  claim 39 , wherein the instructions further cause the processing apparatus to receive instructions from a teacher through a communications interface.