Supervisory control of vehicles

Abstract

Among other things, a command is received expressing an objective for operation of a vehicle within a denominated travel segment of a planned travel route. The objective spans a time series of (for example, is expressed at a higher or more abstract level than) control inputs that are to be delivered to one or more of the brake, accelerator, steering, or other operational actuator of the vehicle. The command is expressed to cause operation of the vehicle along a selected man-made travel structure of the denominated travel segment. A feasible manner of operation of the vehicle is determined to effect the command. A succession of control inputs is generated to one or more of the brake, accelerator, steering or other operational actuator of the vehicle in accordance with the determined feasible manner of operation.

1 . (canceled) 
     
     
         2 . An autonomous vehicle comprising:
 at least one processor; and   a memory storage unit comprising instructions executable by the at least one processor, the instructions comprising instructions to:
 identify, by the at least one processor, a supervisory command comprising a gesture, the supervisory command representing a designated goal; 
 generate, by the at least one processor, a set of candidate trajectories in accordance with the designated goal; 
 identify, by the at least one processor, candidate trajectories of the set of candidate trajectories that are predicted to cause the autonomous vehicle to collide with an object; 
 remove, from the set of candidate trajectories by the at least one processor to generate an updated set of candidate trajectories, the candidate trajectories that were predicted to cause the autonomous vehicle to collide with the object; 
 select, by the at least one processor, a trajectory for operating the autonomous vehicle from the updated set of candidate trajectories; 
 identify, by the at least one processor using the selected trajectory, a travel lane for operating the autonomous vehicle; and 
 operate, by the at least one processor, the autonomous vehicle in accordance with the identified travel lane. 
   
     
     
         3 . The vehicle of  claim 2 , wherein the trajectory is selected in accordance with one or more of a predefined set of rules, common driving practices, or driving preferences of a class of passengers or a passenger. 
     
     
         4 . The vehicle of  claim 2 , wherein the travel lane comprises a plurality of spatial locations within a threshold distance of the selected trajectory. 
     
     
         5 . The vehicle of  claim 2 , wherein the travel lane further comprises a tube-like structure containing at least one candidate trajectory of the set of candidate trajectories. 
     
     
         6 . The vehicle of  claim 2 , wherein the identifying of the travel lane comprises:
 analyzing spatial properties of the selected trajectory and a road; and   identifying connected lane segments that contain the selected trajectory.   
     
     
         7 . The vehicle of  claim 6 , wherein the analyzing of the spatial properties of the selected trajectory and the road comprises:
 discretizing properties of the road into discretized points;   determining whether each discretized point of the discretized points is within a threshold distance of the selected trajectory; and   responsive to a discretized point of the discretized points being within the threshold distance of the selected trajectory, marking the discretized point as part of the travel lane.   
     
     
         8 . The vehicle of  claim 2 , wherein the instructions are further to:
 analyze geometric properties of each candidate trajectory of the set of candidate trajectories and a drivable road surface; and   remove a candidate trajectory responsive to the candidate trajectory crossing a boundary of the drivable road surface.   
     
     
         9 . A memory storage unit of an autonomous vehicle comprising instructions executable by at least one processor, the instructions comprising instructions to:
 identify, by the at least one processor, a supervisory command comprising a gesture, the supervisory command representing a designated goal;   generate, by the at least one processor, a set of candidate trajectories in accordance with the designated goal;   identify, by the at least one processor, candidate trajectories of the set of candidate trajectories that are predicted to cause the autonomous vehicle to collide with an object;   remove, from the set of candidate trajectories by the at least one processor to generate an updated set of candidate trajectories, the candidate trajectories that were predicted to cause the autonomous vehicle to collide with the object;   select, by the at least one processor using the updated set of candidate trajectories, a trajectory for operating the autonomous vehicle;   identify, by the at least one processor using the selected trajectory, a travel lane for operating the autonomous vehicle; and   operate, by the at least one processor, the autonomous vehicle in accordance with the identified travel lane.   
     
     
         10 . The memory storage unit of  claim 9 , wherein the trajectory is selected in accordance with one or more of a predefined set of rules, common driving practices, or driving preferences of a class of passengers or a passenger. 
     
     
         11 . The memory storage unit of  claim 9 , wherein the travel lane comprises a plurality of spatial locations within a threshold distance of the selected trajectory. 
     
     
         12 . The memory storage unit of  claim 9 , wherein the travel lane further comprises a tube-like structure containing at least one candidate trajectory of the set of candidate trajectories. 
     
     
         13 . The memory storage unit of  claim 9 , wherein the identifying of the travel lane comprises:
 analyzing spatial properties of the selected trajectory and a road; and   identifying connected lane segments that contain the selected trajectory.   
     
     
         14 . The memory storage unit of  claim 13 , wherein the analyzing of the spatial properties of the selected trajectory and the road comprises:
 discretizing properties of the road into discretized points;   determining whether each discretized point of the discretized points is within a threshold distance of the selected trajectory; and   responsive to a discretized point of the discretized points being within the threshold distance of the selected trajectory, marking the discretized point as part of the travel lane.   
     
     
         15 . The memory storage unit of  claim 9 , wherein the instructions are further to:
 analyze geometric properties of each candidate trajectory of the set of candidate trajectories and a drivable road surface; and   remove a candidate trajectory responsive to the candidate trajectory crossing a boundary of the drivable road surface.   
     
     
         16 . A method comprising:
 receiving, by at least one processor, a supervisory command comprising a gesture from a passenger of an autonomous vehicle, the supervisory command representing a designated goal;   generating, by the at least one processor of the autonomous vehicle, a set of candidate trajectories in accordance with the designated goal;   identifying, by the at least one processor, candidate trajectories of the set of candidate trajectories that are predicted to cause the autonomous vehicle to collide with an object;   remove, from the set of candidate trajectories by the at least one processor to generate an updated set of candidate trajectories, the candidate trajectories that were predicted to cause the autonomous vehicle to collide with the object;   selecting, by the at least one processor, a trajectory for operating the autonomous vehicle from the updated set of candidate trajectories;   identifying, by the at least one processor using the selected trajectory, a travel lane for operating the autonomous vehicle; and   operating, by the at least one processor, the autonomous vehicle in accordance with the identified travel lane.   
     
     
         17 . The method of  claim 16 , wherein the trajectory is selected in accordance with one or more of a predefined set of rules, common driving practices, or driving preferences of a class of passengers or the passenger. 
     
     
         18 . The method of  claim 16 , wherein the travel lane comprises a plurality of spatial locations within a threshold distance of the selected trajectory. 
     
     
         19 . The method of  claim 16 , wherein the travel lane further comprises a tube-like structure containing at least one candidate trajectory of the set of candidate trajectories. 
     
     
         20 . The method of  claim 16 , wherein the identifying of the travel lane comprises:
 analyzing spatial properties of the selected trajectory and a road; and   identifying connected lane segments that contain the selected trajectory.   
     
     
         21 . The method of  claim 19 , wherein the analyzing of the spatial properties of the selected trajectory and the road comprises:
 discretizing properties of the road into discretized points;   determining whether each discretized point of the discretized points is within a threshold distance of the selected trajectory; and   responsive to a discretized point of the discretized points being within the threshold distance of the selected trajectory, marking the discretized point as part of the travel lane.