Collision monitoring using statistic models

A method comprising:

• receiving sensor data from one or more sensors of a vehicle;
• determining, based at least in part on a first portion of the sensor data, an estimated location associated with the vehicle at a time;
• determining, based at least in part on a system of the vehicle and a second portion of the sensor data, a first estimated location associated with an object at the time;
• receiving an error model associated with the first estimated location associated with the object, the error model determined based at least in part on log data and indicative of a distance between an actual location of the object at the time and the first estimated location of the object at the time;
• determining, based at least in part on the error model and the first estimated location associated with the object at the time, an error distribution of estimated locations associated with the object at the time, the error distribution of estimated locations including at least a first probability associated with the first estimated location associated with the object at the time and a second probability associated with a second estimated location associated with the object at the time;
• and
• causing the vehicle to perform one or more actions based at least in part on the estimated location associated with the vehicle and the error distribution of estimated locations associated with the object.

One or more non-transitory computer-readable media storing instructions that, when executed by one or more processors, cause one or more computing devices to perform operations comprising:

• receiving sensor data generated by a sensor associated with a vehicle;
• determining, based at least in part on a portion of the sensor data, a first estimated location associated with an object at a time;
• receiving an error model determined from a plurality of error models and based at least in part on the first estimated location and log data, the error model indicative of a distance between an actual location associated with the object at the time and the first estimated location associated with the object at the time;
• determining, based at least in part on the error model and the first estimated location associated with the object at the time, an error distribution of estimated locations associated with the object at the time, the error distribution of estimated locations including at least a first probability associated with the first estimated location associated with the object at the time and a second probability associated with a second estimated location associated with the object at the time;
• and
• determining one or more actions for navigating the vehicle based at least in part on the error distribution of estimated locations.