Trainable modular robotic apparatus

Abstract

Apparatus and methods for a modular robotic device with artificial intelligence that is receptive to training controls. In one implementation, modular robotic device architecture may be used to provide all or most high cost components in an autonomy module that is separate from the robotic body. The autonomy module may comprise controller, power, actuators that may be connected to controllable elements of the robotic body. The controller may position limbs of the toy in a target position. A user may utilize haptic training approach in order to enable the robotic toy to perform target action(s). Modular configuration of the disclosure enables users to replace one toy body (e.g., the bear) with another (e.g., a giraffe) while using hardware provided by the autonomy module. Modular architecture may enable users to purchase a single AM for use with multiple robotic bodies, thereby reducing the overall cost of ownership.

1 - 20 . (canceled) 
     
     
         21 . A system for training a device to perform a desired task, comprising:
 a memory having computer readable instructions stored thereon; and   at least one processor, in a learning mode, configured to execute the computer readable instructions to,
 route the device along a desired trajectory by transmitting signals to actuators coupled to the device, 
 receive a teaching input from a user after the device deviates from the desired trajectory, the deviation from the desired trajectory being determined by the user, the teaching input being received at a first trial mode from a plurality of trial phases in the learning mode, 
 detect a trajectory displacement of the device based on the receipt of the teaching input during the first trial mode, the trajectory displacement during the first trial mode including a first numerical value, 
 correspond the trajectory displacement as a change in state of the device, and 
 transfer the route, the teaching input, the trajectory displacement, and the change in state of the device to a different secondary device via an interface. 
   
     
     
         22 . The system of  claim 21 , wherein the teaching input includes a haptic action, the haptic action includes an action selected from a group consisting of push, pull, pick up and move, rotate, grasp, manipulate, release, and bump the robot along the desired trajectory. 
     
     
         23 . The system of  claim 21 , wherein the change in state of the device is based on a modification of one or more parameters of the device, the parameters include motion characteristics of the device selected from the group consisting of speed, acceleration, orientation, rotation, orientation and position of the device. 
     
     
         24 . The system of  claim 21 , wherein the teaching input received by the at least one processor is in the form of at least one of visual signal and audio signal, the visual signal includes recognition of a portion of a user's body, and the audio signal includes an audible command. 
     
     
         25 . The system of  claim 21 , wherein the at least one processor, in an autonomous mode, is further configured to execute the computer readable instructions to,
 adjust the route of the device along the desired trajectory at a second trial mode, the second trial mode is subsequent to the first trial mode, and   detect the trajectory displacement of the device during the second trial mode, the trajectory displacement during the second trial mode including a second numerical value, the second numerical value is smaller than the first numerical value.   
     
     
         26 . A non-transitory computer readable medium having instructions stored thereon that when executed by at least one processor, in a learning mode, configure the at least one processor to,
 route the device along a desired trajectory by transmitting signals to actuators coupled to the device;   receive a teaching input from a user after the device deviates from the desired trajectory, the deviation from the desired trajectory being determined by the user, the teaching input being received at a first trial mode from a plurality of trial phases in the learning mode;   detect a trajectory displacement of the device based on the receipt of the teaching input during the first trial mode, the trajectory displacement during the first trial mode including a first numerical value;   correspond the trajectory displacement as a change in state of the device; and   transfer the route, the teaching input, the trajectory displacement, and the change in state of the device to a different secondary device via an interface.   
     
     
         27 . The non-transitory computer readable medium of  claim 26 , wherein the teaching input includes a haptic action, the haptic action includes an action selected from a group consisting of push, pull, pick up and move, rotate, grasp, manipulate, release, and bump the robot along the desired trajectory. 
     
     
         28 . The non-transitory computer readable medium of  claim 26 , wherein the change in state of the device is based on a modification of one or more parameters of the device, the parameters include motion characteristics of the device selected from the group consisting of speed, acceleration, orientation, rotation, orientation and position of the device. 
     
     
         29 . The non-transitory computer readable medium of  claim 26 , wherein the teaching input received by the at least one processor is in the form of at least one of visual signal and audio signal, the visual signal includes recognition of a portion of a user's body, and the audio signal includes an audible command. 
     
     
         30 . The non-transitory computer readable medium of  claim 26 , wherein the at least one processor, in an autonomous mode, is further configured to execute the computer readable instructions to,
 adjust the route of the device along the desired trajectory at a second trial mode, the second trial mode is subsequent to the first trial mode, and   detect the trajectory displacement of the device during the second trial mode, the trajectory displacement during the second trial mode including a second numerical value, the second numerical value is smaller than the first numerical value.   
     
     
         31 . A method for training a device to perform a desired task, comprising:
 routing the device along a desired trajectory by transmitting signals to actuators coupled to the device;   receiving a teaching input from a user after the device deviates from the desired trajectory, the deviation from the desired trajectory being determined by the user, the teaching input being received at a first trial mode from a plurality of trial phases in the learning mode;   detecting a trajectory displacement of the device based on the receipt of the teaching input during the first trial mode, the trajectory displacement during the first trial mode including a first numerical value;   corresponding the trajectory displacement as a change in state of the device; and   transferring the route, the teaching input, the trajectory displacement, and the change in state of the device to a different secondary device via an interface.   
     
     
         32 . The method of  claim 31 , wherein the teaching input includes a haptic action, the haptic action includes an action selected from a group consisting of push, pull, pick up and move, rotate, grasp, manipulate, release, and bump the robot along the desired trajectory. 
     
     
         33 . The method of  claim 31 , wherein the change in state of the device is based on a modification of one or more parameters of the device, the parameters include motion characteristics of the device selected from the group consisting of speed, acceleration, orientation, rotation, orientation and position of the device. 
     
     
         34 . The method of  claim 31 , wherein the teaching input received by the at least one processor is in the form of at least one of visual signal and audio signal, the visual signal includes recognition of a portion of a user's body, and the audio signal includes an audible command. 
     
     
         35 . The method of  claim 31 , wherein the at least one processor, in an autonomous mode, is further configured to execute the computer readable instructions to,
 adjust the route of the device along the desired trajectory at a second trial mode, the second trial mode is subsequent to the first trial mode, and   detect the trajectory displacement of the device during the second trial mode, the trajectory displacement during the second trial mode including a second numerical value, the second numerical value is smaller than the first numerical value.