Depart constraints implementation in autonomous vehicle routing

Abstract

A method of controlling navigation of autonomous vehicles includes accessing map data descriptive of the identity and location of different travel ways within a surrounding environment of an autonomous vehicle and accessing constraint data descriptive of one or more geographic areas or geographic identifiers, within the map data, for which associated navigational constraints are defined. The constraint data includes a depart constraint that specifies an area that an autonomous vehicle may not enter but may exit if inside the area when the depart constraint is imposed, thereby preventing the autonomous vehicle from being trapped in a forbidden area even though the autonomous vehicle may safely complete its route. A travel route is determined for the autonomous vehicle based at least in part on the map data evaluated relative to the constraint data including the depart constraint, and motion of the autonomous vehicle is controlled based on the determined travel route.

1 . A computer-implemented method of controlling navigation of an autonomous vehicle, comprising:
 accessing event data describing an event at a location in a geographic area;   determining a geographic identifier describing the location;   generating constraint data using the geographic identifier and the event data, the constraint data describing a depart constraint associated with the location, the depart constraint indicating that an autonomous vehicle is permitted to enter the location only from other locations that are also associated with a depart constraint;   determining a travel route for navigating the autonomous vehicle using map data evaluated relative to the constraint data; and   instructing the autonomous vehicle to travel along the determined travel route.   
     
     
         2 . The computer-implemented method of  claim 1 , wherein the depart constraint also indicates that an autonomous vehicle in the location may continue to travel within the location and may exit the location but that an autonomous vehicle outside of the location may not enter the location. 
     
     
         3 . The computer-implemented method of  claim 2 , further comprising modifying a traversal cost of a first travel way portion in the location, the modifying being based at least in part on the depart constraint. 
     
     
         4 . The computer-implemented method of  claim 1 , further comprising controlling motion of the autonomous vehicle based at least in part on the determined travel route. 
     
     
         5 . The computer-implemented method of  claim 1 , the constraint data describing a polygon indicating a boundary of the location. 
     
     
         6 . The computer-implemented method of  claim 1 , further comprising:
 using the constraint data, determining a set of permitted travel way portions from a plurality of travel way portions in the location; and   determining a set of forbidden travel way portions from the plurality of travel way portions in the location using the constraint data, the determining of the travel route being based on the set of permitted travel way portions and the set of forbidden travel way portions.   
     
     
         7 . The computer-implemented method of  claim 6 , the set of permitted travel way portions being described by the constraint data as at least one of having a default permit state, being enclosed by a complete inclusion polygon, or being touched by a partial inclusion polygon. 
     
     
         8 . The computer-implemented method of  claim 6 , the set of forbidden travel way portions being described by the constraint data as at least one of having a default forbid state, being enclosed by a complete exclusion polygon, or being touched by a partial exclusion polygon. 
     
     
         9 . The computer-implemented method of  claim 1 , further comprising:
 generating a map constraint interface, the map constraint interface to receive updates to the constraint data;   receiving, via the map constraint interface, an update to the constraint data; and   sending updated constraint data to at least one AV.   
     
     
         10 . The computer-implemented method of  claim 9 , the map constraint interface comprising a set of constraint layer input fields associated with the map data, the set of constraint layer input fields to toggle activation of the respective constraint layers. 
     
     
         11 . The computer-implemented method of  claim 1 , further comprising determining a set of constraint layers that are active for the map data, the determining of the travel route based on a portion of the set of constraint layers that are active for the map data. 
     
     
         12 . A computing system for controlling navigation of an autonomous vehicle, the computing system comprising:
 at least one processor; and   at least one memory device comprising instructions stored thereon that, when executed by the at least one processor, cause the at least one processor to perform operations comprising:
 accessing event data describing an event at a location in a geographic area; 
 determining a geographic identifier describing the location; 
 generating constraint data using the geographic identifier and the event data, the constraint data describing a depart constraint associated with the location, the depart constraint indicating that an autonomous vehicle is permitted to enter location only from other locations that are also associated with a depart constraint; 
 determining a travel route for navigating the autonomous vehicle using map data evaluated relative to the constraint data; and 
 instructing the autonomous vehicle to travel along the determined travel route. 
   
     
     
         13 . The computing system of  claim 12 , wherein the depart constraint also indicates that an autonomous vehicle in the location may continue to travel within the location and may exit the location but that an autonomous vehicle outside of the location may not enter the location. 
     
     
         14 . The computing system of  claim 13 , the operations further comprising modifying a traversal cost of a first travel way portion in the location, the modifying being based at least in part on the depart constraint. 
     
     
         15 . The computing system of  claim 12 , the operations further comprising controlling motion of the autonomous vehicle based at least in part on the determined travel route. 
     
     
         16 . The computing system of  claim 12 , the constraint data describing a polygon indicating a boundary of the location. 
     
     
         17 . The computing system of  claim 12 , the operations further comprising:
 using the constraint data, determining a set of permitted travel way portions from a plurality of travel way portions in the location; and   determining a set of forbidden travel way portions from the plurality of travel way portions in the location using the constraint data, the determining of the travel route being based on the set of permitted travel way portions and the set of forbidden travel way portions.   
     
     
         18 . The computing system of  claim 17 , the set of permitted travel way portions being described by the constraint data as at least one of having a default permit state, being enclosed by a complete inclusion polygon, or being touched by a partial inclusion polygon. 
     
     
         19 . The computing system of  claim 17 , the set of forbidden travel way portions being described by the constraint data as at least one of having a default forbid state, being enclosed by a complete exclusion polygon, or being touched by a partial exclusion polygon. 
     
     
         20 . A non-transitory computer-readable medium comprising instructions thereon that, when executed by at least one processor, causes the at least one processor to perform operations comprising:
 accessing event data describing an event at a location in a geographic area;   determining a geographic identifier describing the location;   generating constraint data using the geographic identifier and the event data, the constraint data describing a depart constraint associated with the location, the depart constraint indicating that an autonomous vehicle is permitted to enter location only from other locations that are also associated with a depart constraint;   determining a travel route for navigating the autonomous vehicle using map data evaluated relative to the constraint data; and   instructing the autonomous vehicle to travel along the determined travel route.