Systems and methods for determining predicted risk for a flight path of an unmanned aerial vehicle

Abstract

This disclosure relates to systems and methods for determining predicted risk for a flight path of an unmanned aerial vehicle. A previously stored three-dimensional representation of a user-selected location may be obtained. The three-dimensional representation may be derived from depth maps of the user-selected location generated during previous unmanned aerial vehicle flights. The three-dimensional representation may reflect a presence of objects and object existence accuracies for the individual objects. The object existence accuracies for the individual objects may provide information about accuracy of existence of the individual objects within the user-selected location. A user-created flight path may be obtained for a future unmanned aerial flight within the three-dimensional representation of the user-selected location. Predicted risk may be determined for individual portions of the user-created flight path based upon the three-dimensional representation of the user-selected location.

1 - 20 . (canceled) 
     
     
         21 . A system comprising:
 one or more physical processors configured by machine readable instructions to:
 obtain a three-dimensional representation of a location, the three-dimensional representation reflecting a presence of objects and object existence accuracies for each individual object; 
 obtain a flight path for an unmanned aerial flight within the three-dimensional representation of the location; and 
 determine predicted risk for individual portions of the flight path based upon risk parameters by determining a risk confidence score for each individual object, the risk parameters including the object existence accuracies. 
   
     
     
         22 . The system of  claim 21 , wherein the three-dimensional representation is derived from depth maps of the location generated during previous unmanned aerial flights. 
     
     
         23 . The system of  claim 21 , wherein the object existence accuracies provide information about accuracy of existence of each individual object within the location. 
     
     
         24 . The system of  claim 23 , wherein the information about accuracy of existence of each individual object within the location includes information about accuracy of boundaries of each individual object within the location. 
     
     
         25 . The system of  claim 21 , wherein each risk confidence score represents a likelihood of an unmanned aerial vehicle to collide with each corresponding individual object within the three-dimensional representation of the location. 
     
     
         26 . The system of  claim 21 , wherein the risk parameters include a distance between an unmanned aerial vehicle along the individual portions of the flight path and each individual object within the three-dimensional representation and previous collision records of previous unmanned aerial vehicles colliding with an object within the location. 
     
     
         27 . The system of  claim 21 , wherein the predicted risk for a given portion of the flight path reflects likelihood of experiencing a collision with one or more of the objects at or near the given portion of the flight path. 
     
     
         28 . The system of  claim 21 , wherein the object existence accuracies reflect a higher object existence accuracy for stationary objects and a lower object existence accuracy for moving objects. 
     
     
         29 . The system of  claim 21 , wherein the one or more physical processors are further configured by machine readable instructions to:
 track a position of an unmanned aerial vehicle during an unmanned aerial flight; and   determine an updated predicted risk based upon the tracked position of the unmanned aerial vehicle, wherein the updated predicted risk reflects a likelihood of experiencing a collision with one or more objects at or near the tracked position of the unmanned aerial vehicle.   
     
     
         30 . A method comprising:
 obtaining a three-dimensional representation of a user-selected location, the three-dimensional representation reflecting a presence of objects and object existence accuracies for each individual object;   obtaining a user-created flight path for a future unmanned aerial flight within the three-dimensional representation of the user-selected location; and   determining predicted risk for individual portions of the user-created flight path based upon risk parameters by determining a risk confidence score for each individual object, the risk parameters including the object existence accuracies.   
     
     
         31 . The method of  claim 30 , wherein the three-dimensional representation is derived from depth maps of the user-selected location generated during previous unmanned aerial flights. 
     
     
         32 . The method of  claim 30 , wherein the object existence accuracies provide information about accuracy of existence of each individual object within the user-selected location. 
     
     
         33 . The method of  claim 32 , wherein the information about accuracy of existence of each individual object within the user-selected location includes information about accuracy of boundaries of each individual object within the user-selected location. 
     
     
         34 . The method of  claim 30 , wherein each risk confidence score represents a likelihood of an unmanned aerial vehicle to collide with each corresponding individual object within the three-dimensional representation of the user-selected location. 
     
     
         35 . The method of  claim 30 , wherein the risk parameters include a distance between an unmanned aerial vehicle along the individual portions of the user-created flight path and each individual object within the three-dimensional representation and previous collision records of previous unmanned aerial vehicles colliding with an object within the user-selected location. 
     
     
         36 . The method of  claim 30 , wherein the predicted risk for a given portion of the user-created flight path reflects likelihood of experiencing a collision with one or more of the objects at or near the given portion of the user-created flight path. 
     
     
         37 . The method of  claim 30 , wherein the object existence accuracies reflect a higher object existence accuracy for stationary objects and a lower object existence accuracy for moving objects. 
     
     
         38 . The method of  claim 30 , comprising:
 tracking a position of an unmanned aerial vehicle during an unmanned aerial flight; and   determining an updated predicted risk based upon the tracked position of the unmanned aerial vehicle, wherein the updated predicted risk reflects a likelihood of experiencing a collision with one or more objects at or near the tracked position of the unmanned aerial vehicle.   
     
     
         39 . The method of  claim 30 , wherein a first portion of the user-created flight path for which risk is determined is a point on the user-created flight path. 
     
     
         40 . A non-transitory computer-readable storage medium comprising stored instructions that, when executed, causes at least one processor to:
 obtain a three-dimensional representation of a location, the three-dimensional representation reflecting a presence of objects and object existence accuracies for each individual object; and   determine predicted risk for individual portions of a flight path within the three-dimensional representation based upon risk parameters by determining a risk confidence score for each individual object, the risk parameters including the object existence accuracies.