Facilitating Vehicle Driving and Self-Driving

Abstract

Among other things, an operation related to control of a vehicle is facilitated by actions that include the following. A finite set of candidate trajectories of the vehicle is generated that begin at a location of the vehicle as of a given time. The candidate trajectories are based on a state of the vehicle and on possible behaviors of the vehicle and of the environment as of the location of the vehicle and the given time. A putative optimal trajectory is selected from among the candidate trajectories based on costs associated with the candidate trajectories. The costs include costs associated with violations of rules of operation of the vehicle. The selected putative optimal trajectory is used to facilitate the operation related to control of the vehicle.

1 . A method comprising
 effecting an operation related to control of a vehicle by actions that include:   generating a finite set of candidate trajectories of the vehicle as of a given time, the generating of the finite set comprising applying a model that represents the vehicle's expected responses to corresponding control policies for respective candidate trajectories as of the location of the vehicle and the given time,   selecting a putative optimal trajectory from among the candidate trajectories of the finite set based on the corresponding control policies and on costs associated with the candidate trajectories, and   effecting the operation related to control of the vehicle by applying a control policy associated with the selected putative optimal trajectory.   
     
     
         2 . The method of  claim 1  in which each of the control policies determines at least one of steering, braking, or throttling commands. 
     
     
         3 . The method of  claim 1  in which the space of possible trajectories of the vehicle is sufficiently covered by the generated finite set of candidate trajectories so that the putative optimal strategy is arbitrarily close to the optimal strategy. 
     
     
         4 . The method of  claim 1  comprising applying one or more constraints to the finite set of candidate trajectories. 
     
     
         5 . The method of  claim 1  comprising representing the candidate trajectories as edges of a directed graph. 
     
     
         6 . The method of  claim 1  comprising monitoring an actual trajectory of the vehicle for a given time period. 
     
     
         7 . The method of  claim 6  comprising comparing, for the given time period, the actual trajectory of the vehicle with the putative optimal trajectory. 
     
     
         8 . The method of  claim 1  in which the effecting of an operation related to control of a vehicle comprises monitoring a driver's performance. 
     
     
         9 . The method of  claim 8  comprising reporting a result of the monitoring of the driver's performance. 
     
     
         10 . The method of  claim 8  comprising evaluating the driver's performance based on one or more performance metrics. 
     
     
         11 . The method of  claim 8  comprising assessing the likelihood of an accident occurring. 
     
     
         12 . The method of  claim 1  in which effecting an operation related to control of a vehicle comprises autonomously driving the vehicle. 
     
     
         13 . The method of  claim 1  in which the costs associated with a given trajectory are based on costs associated with interactions between the states of the vehicle and states of the environment. 
     
     
         14 . The method of  claim 1  in which the selected putative optimal trajectory is associated with both speed and direction of the vehicle. 
     
     
         15 . The method of  claim 1  in which selecting the putative optimal trajectory comprises determining a minimum-cost path through a directed graph of which the candidate trajectories comprise edges. 
     
     
         16 . An apparatus comprising
 an autonomous vehicle comprising   controllable devices configured to cause the vehicle to traverse at least part of an optimal trajectory in a manner consistent with cost rules,   a controller to provide commands to the controllable devices in accordance with the optimal trajectory, and   a computational element configured to effect, through the controllable devices, an operation related to control of the vehicle, by actions that include:
 generating a finite set of candidate trajectories of the vehicle as of a given time, the generating of the finite set comprising applying a model that represents the vehicle's expected responses to corresponding control policies for respective candidate trajectories as of the location of the vehicle and the given time, 
 selecting a putative optimal trajectory from among the candidate trajectories of the finite set based on the corresponding control policies and on costs associated with the candidate trajectories, and 
 effecting the operation related to control of the vehicle by applying a control policy associated with the optimal trajectory. 
   
     
     
         17 . The method of  claim 16  in which each of the control policies determines at least one of steering, braking, or throttling commands. 
     
     
         18 . The method of  claim 16  in which the space of possible trajectories of the vehicle is sufficiently covered by the generated finite set of candidate trajectories so that the putative optimal strategy is arbitrarily close to the optimal strategy. 
     
     
         19 . The method of  claim 16  comprising applying one or more constraints to the finite set of candidate trajectories. 
     
     
         20 . The method of  claim 16  comprising representing the candidate trajectories as edges of a directed graph. 
     
     
         21 . The method of  claim 16  comprising monitoring an actual trajectory of the vehicle for a given time period. 
     
     
         22 . The method of  claim 21  comprising comparing, for the given time period, the actual trajectory of the vehicle with the putative optimal trajectory. 
     
     
         23 . The method of  claim 16  in which the effecting of an operation related to control of a vehicle comprises monitoring a driver's performance. 
     
     
         24 . The method of  claim 23  comprising reporting a result of the monitoring of the driver's performance. 
     
     
         25 . The method of  claim 23  comprising evaluating the driver's performance based on one or more performance metrics. 
     
     
         26 . The method of  claim 23  comprising assessing the likelihood of an accident occurring. 
     
     
         27 . The method of  claim 16  in which effecting an operation related to control of a vehicle comprises autonomously driving the vehicle. 
     
     
         28 . The method of  claim 16  in which the costs associated with a given trajectory are based on costs associated with interactions between the states of the vehicle and states of the environment. 
     
     
         29 . The method of  claim 16  in which the selected putative optimal trajectory is associated with both speed and direction of the vehicle. 
     
     
         30 . The method of  claim 16  in which selecting the putative optimal trajectory comprises determining a minimum-cost path through a directed graph of which the candidate trajectories comprise edges.