Drop-off location planning for delivery vehicle

Abstract

An example method may include receiving, from a client computing device, an indication of a target drop-off spot for an object within a first virtual model of a first region of a delivery destination. A second virtual model of a second region of the delivery destination may be determined based on sensor data received from one or more sensors on a delivery vehicle. A mapping may be determined between physical features represented in the first virtual model and physical features represented in the second virtual model to determine an overlapping region between the first and second virtual models. A position of the target drop-off spot within the second virtual model may be determined based on the overlapping region. Based on the position of the target drop-off spot within the second virtual model, the delivery vehicle may be navigated to the target drop-off spot to drop off the object.

1 . (canceled) 
     
     
         2 . A method comprising:
 receiving, from a client computing device, an indication of a target drop-off spot for an object within a first virtual model of a first region, the first virtual model indicating first physical features including three-dimensional relationships between objects in the first region;   obtaining a second virtual model of a second region, the second virtual model indicating second physical features including three-dimensional relationships between objects in the second region;   determining, based on a comparison between the first virtual model and the second virtual model, that a mapping is not found between the first physical features and the second physical features;   in response to determining that the mapping is not found:
 obtaining an additional virtual model indicating third physical features including three-dimensional relationships between objects in a third region; 
 determining a mapping between one or more of the first physical features and one or more of the third physical features to determine an overlapping region between the first virtual model and the additional virtual model; and 
 determining, based on the overlapping region, a position of the target drop-off spot within the additional virtual model; and 
 providing instructions that cause a delivery vehicle to navigate to the target drop-off spot to place the object at the target drop-off spot. 
   
     
     
         3 . The method of  claim 2 , wherein the first virtual model is determined from multiple images captured by the client computing device and first sensor data corresponding to the multiple images. 
     
     
         4 . The method of  claim 2 , further comprising:
 receiving, from one or more sensors on the delivery vehicle, second sensor data indicative of the second region; and   determining the second virtual model based on the second sensor data.   
     
     
         5 . The method of  claim 4 , wherein obtaining the additional model comprises:
 providing, to the delivery vehicle, instructions to scan additional regions in response to determining that the mapping is not found;   receiving, from the one or more sensors one the delivery vehicle, third sensor data indicative of the third region; and   generating the additional model by updating the second virtual model based on the third sensor data.   
     
     
         6 . The method of  claim 5 , wherein the instructions to scan the additional regions comprise instructions to scan the additional regions until a region is found that overlaps with the first region. 
     
     
         7 . The method of  claim 2 , wherein the additional virtual model comprises a master virtual model that indicates physical features including three-dimensional relationships between objects in a general region that includes the first region, the second region, and the third region. 
     
     
         8 . The method of  claim 7 , wherein determining the mapping between one or more of the first physical features and one or more of the third physical features to determine the overlapping region between the first virtual model and the third virtual model comprises:
 determining a first mapping between the first virtual model and the master virtual model;   determining a second mapping between the second virtual model and the master virtual model;   determining, based on the first mapping and the second mapping, a relative geographic positioning of the second region of the second virtual model with respect to the first region of the first virtual model; and   determining, based on the relative geographic positioning of the second region with respect to the first region, the position of the target drop-off spot within the second virtual model.   
     
     
         9 . The method of  claim 8 , wherein providing instructions that cause the delivery vehicle to navigate to the target drop-off spot to place given object at the target drop-off spot comprises determining a trajectory from a current position of the delivery vehicle to the position of the target drop-off spot within the second virtual model. 
     
     
         10 . The method of  claim 8 , further comprising updating the master model using images captured by the delivery vehicle while navigating to the target drop-off spot. 
     
     
         11 . A system comprising:
 a delivery vehicle;   one or more sensors connected to the delivery vehicle; and   a control system configured to:
 receive, from a client computing device, an indication of a target drop-off spot for an object within a first virtual model of a first region, the first virtual model indicating first physical features including three-dimensional relationships between objects in the first region; 
 obtain a second virtual model of a second region, the second virtual model indicating second physical features including three-dimensional relationships between objects in the second region; 
 determine, based on a comparison between the first virtual model and the second virtual model, that a mapping is not found between the first physical features and the second physical features; 
 in response to determining that the mapping is not found:
 obtain an additional virtual model indicating third physical features including three-dimensional relationships between objects in a third region; 
 determine a mapping between one or more of the first physical features and one or more of the third physical features to determine an overlapping region between the first virtual model and the additional virtual model; and 
 determine, based on the overlapping region, a position of the target drop-off spot within the additional virtual model; and 
 provide instructions that cause a delivery vehicle to navigate to the target drop-off spot to place the object at the target drop-off spot. 
 
   
     
     
         12 . The system of  claim 11 , wherein the first virtual model is determined from multiple images captured by the client computing device and first sensor data corresponding to the multiple images. 
     
     
         13 . The system of  claim 11 , wherein the control system is configured to:
 receive, from one or more sensors on the delivery vehicle, second sensor data indicative of the second region; and   determine the second virtual model based on the second sensor data.   
     
     
         14 . The system of  claim 13 , wherein obtaining the additional model comprises:
 providing, to the delivery vehicle, instructions to scan additional regions in response to determining that the mapping is not found;   receiving, from the one or more sensors one the delivery vehicle, third sensor data indicative of the third region; and   generating the additional model by updating the second virtual model based on the third sensor data.   
     
     
         15 . The system of  claim 14 , wherein the instructions to scan the additional regions comprise instructions to scan the additional regions until a region is found that overlaps with the first region. 
     
     
         16 . The system of  claim 11 , wherein the additional virtual model comprises a master virtual model that indicates physical features including three-dimensional relationships between objects in a general region that includes the first region, the second region, and the third region. 
     
     
         17 . The system of  claim 16 , wherein determining the mapping between one or more of the first physical features and one or more of the third physical features to determine the overlapping region between the first virtual model and the third virtual model comprises:
 determining a first mapping between the first virtual model and the master virtual model;   determining a second mapping between the second virtual model and the master virtual model;   determining, based on the first mapping and the second mapping, a relative geographic positioning of the second region of the second virtual model with respect to the first region of the first virtual model; and   determining, based on the relative geographic positioning of the second region with respect to the first region, the position of the target drop-off spot within the second virtual model.   
     
     
         18 . The system of  claim 17 , wherein providing instructions that cause the delivery vehicle to navigate to the target drop-off spot to place given object at the target drop-off spot comprises determining a trajectory from a current position of the delivery vehicle to the position of the target drop-off spot within the second virtual model. 
     
     
         19 . The system of  claim 18 , wherein the control system is configured to update the master model using images captured by the delivery vehicle while navigating to the target drop-off spot. 
     
     
         20 . A non-transitory computer readable storage medium having stored thereon instructions that, when executed by a computing device, cause the computing device to perform operations comprising:
 receiving, from a client computing device, an indication of a target drop-off spot for an object within a first virtual model of a first region, the first virtual model indicating first physical features including three-dimensional relationships between objects in the first region;   obtaining a second virtual model of a second region, the second virtual model indicating second physical features including three-dimensional relationships between objects in the second region;   determining, based on a comparison between the first virtual model and the second virtual model, that a mapping is not found between the first physical features and the second physical features;   in response to determining that the mapping is not found:
 obtaining an additional virtual model indicating third physical features including three-dimensional relationships between objects in a third region; 
 determining a mapping between one or more of the first physical features and one or more of the third physical features to determine an overlapping region between the first virtual model and the additional virtual model; and 
 determining, based on the overlapping region, a position of the target drop-off spot within the additional virtual model; and 
 providing instructions that cause a delivery vehicle to navigate to the target drop-off spot to place the object at the target drop-off spot. 
   
     
     
         21 . The non-transitory computer readable storage medium of  claim 20 , wherein the first virtual model is determined from multiple images captured by the client computing device and first sensor data corresponding to the multiple images.