Systems and methods for initializing a robot to autonomously travel a trained route

Abstract

Systems and methods for initializing a robot to autonomously travel a route are disclosed. In some exemplary implementations, a robot can detect an initialization object and then determine its position relative to that initialization object. The robot can then learn a route by user demonstration, where the robot associates actions along that route with positions relative to the initialization object. The robot can later detect the initialization object again and determine its position relative to that initialization object. The robot can then autonomously navigate the learned route, performing actions associated with positions relative to the initialization object.

1 - 26 . (canceled) 
     
     
         27 . A system for maneuvering a robot, comprising:
 a memory including computer readable instructions stored thereon; and   at least one processor configured to execute the computer readable instructions to,
 determine, in a learning mode, position of the robot relative to an initialization object at a first location, 
 route, in the learning mode, the robot from the first location to a second location along a desired path, 
 store, in the learning mode, the initialization object and a plurality of actions demonstrated by a user with respect to a particular position along the desired path while the robot travels the route from the first location to the second location, and 
 associate, in the learning mode, the route and the plurality of actions to the initialization object. 
   
     
     
         28 . The system of  claim 27 , wherein the at least one processor is further configured to execute the computer readable instructions to,
 determine, in an autonomous mode, position of the robot relative to the initialization object, the autonomous mode is different from the learning mode, and   upload, in the autonomous mode, the route and the plurality of actions learned in the learning mode if there is a match between the initialization object identified in the autonomous mode and the learning mode.   
     
     
         29 . The system of  claim 28 , wherein the at least one processor is further configured to execute the computer readable instructions to,
 route, in the autonomous mode, the robot from the first location to the second location, and   execute, in the autonomous mode, the plurality of actions with respect to the particular position along the desired path demonstrated by the user during the learning mode.   
     
     
         30 . The system of  claim 29 , wherein the at least processor is further configured to execute the computer readable instructions to,
 store a library of images of initialization object, the initialization object is a binary image and asymmetrical, and the initialization object is associated with at least one learned route such that detection of the initialization object from the library of images of initialization object causes the robot to execute the plurality of actions in the autonomous mode.   
     
     
         31 . The system of  claim 27 , wherein the at least one processor is further configured to execute the computer readable instructions to enable at least one of an odometry unit and a sensor after the position of the robot is determined relative to the initialization object. 
     
     
         32 . The system of  claim 27 , wherein the robot is at least one selected from the group consisting of a floor scrubber, a vacuum cleaner, a steamer, a mop, and a sweeper. 
     
     
         33 . The system of  claim 27 , wherein the plurality of actions include at least one selected from the group consisting of regulating water flow, turning on or off water supply, turning on or off vacuum, moving vacuum hose position, raising or lower a life, and turning or off a sensor. 
     
     
         34 . The system of  claim 27 , wherein if the robot is a floor cleaner, then at least one of the plurality of actions is regulating water flow and turning on or off the water supply such that only the particular position along the desired path is cleaned. 
     
     
         35 . A method for maneuvering a robot, comprising:
 determining, in a learning mode, position of the robot relative to an initialization object at a first location;   routing, in the learning mode, the robot from the first location to a second location along a desired path;   storing, in the learning mode, the initialization object and a plurality of actions demonstrated by a user with respect to a particular position along the desired path while the robot travels the route from the first location to the second location; and   associating, in the learning mode, the route and the plurality of actions to the initialization object.   
     
     
         36 . The method of  claim 35 , further comprising:
 determining, in an autonomous mode, position of the robot relative to the initialization object, the autonomous mode is different from the learning mode; and   uploading, in the autonomous mode, the route and the plurality of actions learned in the learning mode if there is a match between the initialization object identified in the autonomous mode and the learning mode.   
     
     
         37 . The method of  claim 36 , further comprising:
 routing, in the autonomous mode, the robot from the first location to the second location; and   executing, in the autonomous mode, the plurality of actions with respect to the particular position along the desired path demonstrated by the user during the learning mode.   
     
     
         38 . The method of  claim 37 , further comprising:
 storing a library of images of initialization object, the initialization object is a binary image and asymmetrical, and the initialization object is associated with at least one learned route such that detection of the initialization object from the library of images of initialization object causes the robot to execute the plurality of actions in the autonomous mode.   
     
     
         39 . The method of  claim 35 , further comprising:
 enabling at least one of an odometry unit and a sensor after the position of the robot is determined relative to the initialization object.   
     
     
         40 . The method of  claim 35 , wherein the robot is at least one selected from the group consisting of a floor scrubber, a vacuum cleaner, a steamer, a mop, and a sweeper. 
     
     
         41 . The method of  claim 35 , wherein the plurality of actions include at least one selected from the group consisting of regulating water flow, turning on or off water supply, turning on or off vacuum, moving vacuum hose position, raising or lower a life, and turning or off a sensor. 
     
     
         42 . The method of  claim 35 , wherein if the robot is a floor cleaner, then at least one of the plurality of actions is regulating water flow and turning on or off the water supply such that only the particular position along the desired path is cleaned. 
     
     
         43 . A non-transitory computer readable medium having computer readable instructions stored thereon that when executed by at least one processor configure the at least one processor to,
 determine, in a learning mode, position of the robot relative to an initialization object at a first location,   route, in the learning mode, the robot from the first location to a second location along a desired path,   store, in the learning mode, the initialization object and a plurality of actions demonstrated by a user with respect to a particular position along the desired path while the robot travels the route from the first location to the second location, and   associate, in the learning mode, the route and the plurality of actions to the initialization object.   
     
     
         44 . The non-transitory computer readable medium of  claim 43 , wherein the at least one processor is further configured to execute the computer readable instructions to,
 determine, in an autonomous mode, position of the robot relative to the initialization object, the autonomous mode is different from the learning mode, and   upload, in the autonomous mode, the route and the plurality of actions learned in the learning mode if there is a match between the initialization object identified in the autonomous mode and the learning mode.   
     
     
         45 . The non-transitory computer readable medium of  claim 44 , wherein the at least one processor is further configured to execute the computer readable instructions to,
 route, in the autonomous mode, the robot from the first location to the second location, and   execute, in the autonomous mode, the plurality of actions with respect to the particular position along the desired path demonstrated by the user during the learning mode.   
     
     
         46 . The non-transitory computer readable medium of  claim 45 , wherein the at least one processor is further configured to execute the computer readable instructions to,
 store a library of images of initialization object, the initialization object is a binary image and asymmetrical, and the initialization object is associated with at least one learned route such that detection of the initialization object from the library of images of initialization object causes the robot to execute the plurality of actions in the autonomous mode.