Testing a scheduling system for autonomous vehicles using simulations

A system comprising a simulation system including one or more computing devices configured to:

• identify a problem condition related to scheduling and dispatching of a fleet of autonomous vehicles and associated with a particular autonomous vehicle of the fleet of autonomous vehicles;
• run, using map information common to the fleet of autonomous vehicles, a first portion of a simulation of the fleet of autonomous vehicles;
• run, using the map information, a second portion of the simulation including occurrence of the problem condition, the second portion of the simulation being subsequent to the first portion of the simulation;
• run, using the map information, a third portion of the simulation including a response of a scheduling system to the problem condition, the third portion of the simulation being subsequent to the second portion of the simulation,
• wherein the first portion, the second portion and the third portion of the simulation includes:
• generation of, by respective autonomous vehicle control of each autonomous vehicle of the fleet of autonomous vehicles, a respective route to a respective destination;
• control of, by the respective autonomous vehicle control of each autonomous vehicle of the fleet of autonomous vehicles, the autonomous vehicle along at least a portion of the respective route;
• and
• simulation of scheduling and dispatching of the fleet of autonomous vehicles by the scheduling system;
• determine, a score associated with the scheduling and dispatching of the fleet of autonomous vehicles by the scheduling system during at least the third portion of the simulation;
• and
• evaluate, based at least on the score, one or more decisions by the scheduling system during at least the third portion of the simulation.

A non-transitory computer-readable medium on which instructions are stored, the instructions, when executed by one or more processors cause the one or more processors to perform a method comprising:

• identifying a problem condition related to scheduling and dispatching of a fleet of autonomous vehicles and associated with a particular autonomous vehicle of the fleet of autonomous vehicles;
• running, using map information common to the fleet of autonomous vehicles, a first portion of a simulation of the fleet of autonomous vehicles;
• running, using the map information, a second portion of the simulation including occurrence of the problem condition, the second portion of the simulation being subsequent to the first portion of the simulation;
• running, using the map information, a third portion of the simulation including a response of a scheduling system to the problem condition, the third portion of the simulation being subsequent to the second portion of the simulation,
• wherein running the first portion, the second portion and the third portion of the simulation includes:
• generating, by respective autonomous vehicle control of each autonomous vehicle of the fleet of autonomous vehicles, a respective route to a respective destination;
• controlling, by the respective autonomous vehicle control of each autonomous vehicle of the fleet of autonomous vehicles, the autonomous vehicle along at least a portion of the respective route;
• and
• simulating scheduling and dispatching of the fleet of autonomous vehicles by the scheduling system;
• determining a score associated with the scheduling and dispatching of the fleet of autonomous vehicles by the scheduling system during at least the third portion of the simulation;
• and
• evaluating, based at least on the score, one or more decisions by the scheduling system during at least the third portion of the simulation.