Stranding and scoping analysis for autonomous vehicle services

A system for identifying problematic areas within a service area for an autonomous vehicle transportation service, the system comprising:

• one or more computing devices having one or more processors configured to:
• identify a starting location within the service area;
• identify a destination location within the service area;
• run a first simulation to determine a first route for a simulated vehicle to travel between the starting location and the destination location;
• determine that the first route includes performance of a particular type of maneuver at a given location that the simulated vehicle is unlikely to be able to complete;
• based on a determination that the first route includes the performance of the particular type of maneuver at the given location that the simulated vehicle is unlikely to be able to complete, run a second simulation to determine a second route for the simulated vehicle to travel between at least the given location and the destination location,
• wherein:
• the second route does not include the performance of the particular type of maneuver at the given location that the simulated vehicle is unlikely to be able to complete, and
• the second route is different from the first route;
• determine whether the simulated vehicle reaches the destination location in the second simulation;
• and
• based on a determination that the simulated vehicle does not reach the destination location in the second simulation, flag at least one of the starting location or the destination location as potentially problematic areas.

A method of identifying problematic areas within a service area for an autonomous vehicle transportation service, the method comprising:

• identifying, by one or more processors, a starting location within the service area;
• identifying, by the one or more processors, a destination location within the service area;
• running, by the one or more processors, a first simulation to determine a first route for a simulated vehicle to travel between the starting location and the destination location;
• determining, by the one or more processors, that the first route includes performance of a particular type of maneuver at a given location that the simulated vehicle is unlikely to be able to complete;
• based on a determination by the one or more processors that the first route includes the performance of the particular type of maneuver at the given location that the simulated vehicle is unlikely to be able to complete, running, by the one or more processors, a second simulation to determine a second route for the simulated vehicle to travel between the starting location and the destination location without allowing the simulated vehicle to complete the particular type of maneuver at the given location that the simulated vehicle is unlikely to be able to complete,
• wherein:
• the second route being the same as the first route between the starting location and the given location, and
• the second route is different from the first route;
• determining, by the one or more processors, whether the simulated vehicle reaches the destination location in the second simulation;
• and
• based on a determination by the one or more processors that the simulated vehicle does not reach the destination location in the second simulation, flagging, by the one or more processors, at least one of the starting location or the destination location as potentially problematic areas.