Probabilistic navigation system and method

A probabilistic navigation system, comprising

• a processor;
• and
• a non-transitory computer-readable storage medium storing instructions that, when executed by the processor, cause the system to perform a probabilistic navigation method, the method comprising:
• obtaining a map of an environment comprising a plurality of first objects each associated with a probability model, the environment comprising a metropolitan area, and the plurality of first objects including a first static object of the metropolitan area and a first dynamic object of the metropolitan area, the probability model at least describing probability fields of a second object colliding with each of the plurality of first objects, the probability fields decaying away from one or more physical boundaries of each of the plurality of first objects, the density and shape of each the probability fields being based on one or more physical properties of a corresponding first object of the plurality of first objects, the second object comprising an autonomous vehicle;
• obtaining one or more global factors, the one or more global factors including a global weather condition;
• obtaining one or more local factors, the one or more local factors including a local road condition, the one or more local factors being captured by one or more sensors disposed on the second object;
• updating the probability fields of the probability models based on the one or more global factors and the one or more local factors, wherein the global factors relatively apply to all of the first objects, and the local factors apply to a portion of the first objects, wherein at least a first global factor has a first degree of influence for the first static object and the first global factor has a second degree of influence for the first dynamic object, the first degree of influence being different from the second degree of influence, the updating including adjusting a rate of decay for at least one of the probability fields of a corresponding probability of the plurality of probability models;
• and
• determining a navigation for the second object through at least a part of the environment based at least on minimizing a total collision probability of the second object with the plurality of first objects along the navigation according to the updated probability models;
• autonomously causing, in response to determining the navigation, the navigation of the second object through at least the part of the environment.