Method of locating a sensor and related apparatus

Abstract

A method of localising a vehicle hosting a sensor comprises capturing data from the sensor providing a sensed scene around the vehicle at a current time, processing the sensed scene to extract a set of features from the sensed scene and determine a position of the vehicle from the sensed scene in relation to a previous position of the sensor, comparing the extracted set of features to one or more stored experiences, wherein each stored experience comprises a plurality of sets of features, where each set of features has been determined from a previously sensed scene, to ascertain whether the sensed scene can be recognised within any of the stored experiences, and if the extracted set of features of the sensed scene are recognised then that stored experience is used to produce an estimate of the position of the vehicle at the current time with respect to the stored experience.

1 . A method of localising a vehicle hosting a vehicle sensor, comprising the steps of:
 capturing data from the vehicle sensor providing a single representation of an environment around the vehicle at a current time;   extracting a set of nodes from the single representation;   comparing the extracted set of nodes from the single representation to nodes of a plurality of independent stored collections of single representations; and   if the comparison recognises the extracted set of nodes from the single representation within an independent stored collection of single representations, producing an estimate of the position of the vehicle via linking an extracted node to a node in the stored collection of single representations in which the extracted set of nodes is recognised.   
     
     
         2 . The method of  claim 1 , further comprising:
 determining that the extracted set of nodes from the single representation is not recognised within more than a predetermined number of the independent stored collections of single representations; and   responsive to determining the extracted set of nodes is not recognised within more than the predetermined number of the independent stored collections of single representations, storing the single representation as a new independent collection of single representations.   
     
     
         3 . The method of  claim 1 , further comprising:
 using a transformation to determine motion of the vehicle by determining movement of the extracted set of nodes relative to positions of nodes in an earlier single representation captured at an earlier time.   
     
     
         4 . The method of  claim 1 , wherein the comparing comprises:
 determining a coarse position of the vehicle sensor; and   selecting a subset of the plurality of independent stored collections of single representations responsive to the coarse position;   wherein the comparing compares the extracted set of nodes from the single representation to nodes of only the selected subset of independent stored collections of single representations.   
     
     
         5 . The method of  claim 1 , wherein each independent stored collection of single representations represents at least a portion of an environment through which the vehicle moves, and wherein each independent stored collection of single representations relates to a different time and/or date of capture. 
     
     
         6 . The method of  claim 1 , wherein the comparing further comprises:
 comparing the extracted set of nodes from the single representation to a plurality of ones of the plurality of independent stored collections of single representations in parallel at a same time.   
     
     
         7 . The method of  claim 1 , wherein the plurality of independent stored collections of single representations each represent a same physical space of the environment. 
     
     
         8 . A system for localising a vehicle hosting a vehicle sensor, the system comprising:
 a computer processor for executing computer program instructions; and   a non-transitory computer-readable memory storing instructions executable by the processor to perform steps comprising:
 capturing data from the vehicle sensor providing a single representation of an environment around the vehicle at a current time; 
 extracting a set of nodes from the single representation; 
 comparing the extracted set of nodes from the single representation to nodes of a plurality of independent stored collections of single representations; and 
 if the comparison recognises the extracted set of nodes from the single representation within an independent stored collection of single representations, producing an estimate of the position of the vehicle via linking an extracted node to a node in the stored collection of single representations in which the extracted set of nodes is recognised. 
   
     
     
         9 . The system of  claim 8 , the steps further comprising:
 determining that the extracted set of nodes from the single representation is not recognised within more than a predetermined number of the independent stored collections of single representations; and   responsive to determining the extracted set of nodes is not recognised within more than the predetermined number of the independent stored collections of single representations, storing the single representation as a new independent collection of single representations.   
     
     
         10 . The system of  claim 8 , the steps further comprising:
 using a transformation to determine motion of the vehicle by determining movement of the extracted set of nodes relative to positions of nodes in an earlier single representation captured at an earlier time.   
     
     
         11 . The system of  claim 8 , wherein the comparing comprises:
 determining a coarse position of the vehicle sensor; and   selecting a subset of the plurality of independent stored collections of single representations responsive to the coarse position;   wherein the comparing compares the extracted set of nodes from the single representation to nodes of only the selected subset of independent stored collections of single representations.   
     
     
         12 . The system of  claim 8 , wherein each independent stored collection of single representations represents at least a portion of an environment through which the vehicle moves, and wherein each independent stored collection of single representations relates to a different time and/or date of capture. 
     
     
         13 . The system of  claim 8 , wherein the comparing further comprises:
 comparing the extracted set of nodes from the single representation to a plurality of ones of the plurality of independent stored collections of single representations in parallel at a same time.   
     
     
         14 . The system of  claim 8 , wherein the plurality of independent stored collections of single representations each represent a same physical space of the environment. 
     
     
         15 . A non-transitory computer-readable memory storing instructions executable by a computer processor to localise a vehicle hosting a vehicle sensor, the memory storing instructions executable by the processor to perform steps comprising:
 capturing data from the vehicle sensor providing a single representation of an environment around the vehicle at a current time;   extracting a set of nodes from the single representation;   comparing the extracted set of nodes from the single representation to nodes of a plurality of independent stored collections of single representations; and   if the comparison recognises the extracted set of nodes from the single representation within an independent stored collection of single representations, producing an estimate of the position of the vehicle via linking an extracted node to a node in the stored collection of single representations in which the extracted set of nodes is recognised.   
     
     
         16 . The non-transitory computer-readable memory of  claim 15 , the steps further comprising:
 determining that the extracted set of nodes from the single representation is not recognised within more than a predetermined number of the independent stored collections of single representations; and   responsive to determining the extracted set of nodes is not recognised within more than the predetermined number of the independent stored collections of single representations, storing the single representation as a new independent collection of single representations.   
     
     
         17 . The non-transitory computer-readable memory of  claim 15 , the steps further comprising:
 using a transformation to determine motion of the vehicle by determining movement of the extracted set of nodes relative to positions of nodes in an earlier single representation captured at an earlier time.   
     
     
         18 . The non-transitory computer-readable memory of  claim 15 , wherein the comparing comprises:
 determining a coarse position of the vehicle sensor; and   selecting a subset of the plurality of independent stored collections of single representations responsive to the coarse position;   wherein the comparing compares the extracted set of nodes from the single representation to nodes of only the selected subset of independent stored collections of single representations.   
     
     
         19 . The non-transitory computer-readable memory of  claim 15 , wherein each independent stored collection of single representations represents at least a portion of an environment through which the vehicle moves, and wherein each independent stored collection of single representations relates to a different time and/or date of capture. 
     
     
         20 . The non-transitory computer-readable memory of  claim 15 , wherein the comparing further comprises:
 comparing the extracted set of nodes from the single representation to a plurality of ones of the plurality of independent stored collections of single representations in parallel at a same time.