Probabilistic navigation system and method

1. A method, comprising:

obtaining a map of an environment comprising a plurality of objects each associated with a probability model, each of the probability models at least describing one or more probability fields of a vehicle colliding with at least one of the plurality of objects;

obtaining, using the vehicle, one or more global factors from one or more data stores;

obtaining, using one or more sensors, one or more local factors;

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 apply to all of the objects, and the local factors apply to a portion of the objects, wherein at least a first global factor has a first degree of influence for a particular object of the plurality of objects, and wherein the first global factor has a second degree of influence for another object of the plurality of objects, the updating including adjusting a rate of decay for at least one of the probability fields of a corresponding probability model of the plurality of probability models;

determining a navigation for the vehicle through at least a part of the environment based at least on a total collision probability of the vehicle with at least one of the plurality of objects along the navigation according to the updated probability models; and

causing, in response to determining the navigation, the navigation of the vehicle through at least the part of the environment.

2. The method of claim 1 , wherein:

the objects comprise static and dynamic objects, the particular object comprises a particular static object, and the other object comprises a particular dynamic object;

the static objects are substantially stationary with respect to ground; and

the dynamic objects are movable with respect to ground.

3. The method of claim 1 , wherein:

the one or more global factors comprise at least one of weather, a global traffic condition, a season, a time, or a geographic location of the environment; and

the one or more local factors comprise at least one of a local event, a local traffic condition, a local road condition, or one or more of the objects along the navigation.

4. The method of claim 1 , wherein the one or more sensors are disposed at least on the vehicle or along a path of the navigation to monitor and dynamically update the local factors.

5. The method of claim 1 , wherein the total collision probability with at least one of the objects along the navigation comprises a summation of probabilities of colliding with the objects along the navigation.

6. The method of claim 1 , wherein determining the navigation for the vehicle through at least the part of the environment based at least on the total collision probability with at least one of the objects along the navigation according to the updated probability models comprises:

determining the navigation for the vehicle through at least the part of the environment based at least on:

minimizing the total collision probability with the objects along the navigation according to the updated probability models, and

satisfying one or more constraints comprising at least one of minimizing a trip time, minimizing a trip distance, minimizing a trip cost, limiting energy consumption, or fulfilling a user request.

7. The method of claim 1 , further comprising controlling the vehicle to move according to the determined navigation, wherein the navigation comprises at least one of a route, a moving speed, or a moving direction.

8. A computing system comprising:

one or more processors; and

memory storing instructions that, when executed by the one or more processors, cause the computing system to perform operations comprising:

obtaining a map of an environment comprising a plurality of objects each associated with a probability model, each of the probability models at least describing one or more probability fields of a vehicle colliding with at least one of the plurality of objects;

obtaining, using the vehicle, one or more global factors from one or more data stores;

obtaining, using one or more sensors, one or more local factors;

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 apply to all of the objects, and the local factors apply to a portion of the objects, wherein at least a first global factor has a first degree of influence for a particular object of the plurality of objects, and wherein the first global factor has a second degree of influence for another object of the plurality of objects, the updating including adjusting a rate of decay for at least one of the probability fields of a corresponding probability model of the plurality of probability models;

determining a navigation for the vehicle through at least a part of the environment based at least on a total collision probability of the vehicle with at least one of the plurality of objects along the navigation according to the updated probability models; and

causing, in response to determining the navigation, the navigation of the vehicle through at least the part of the environment.

9. The system of claim 8 , wherein:

the objects comprise static and dynamic objects, the particular object comprises a particular static object, and the other object comprises a particular dynamic object;

the static objects are substantially stationary with respect to ground; and

the dynamic objects are movable with respect to ground.

10. The system of claim 8 , wherein:

the one or more global factors comprise at least one of weather, a global traffic condition, a season, a time, or a geographic location of the environment; and

the one or more local factors comprise at least one of a local event, a local traffic condition, a local road condition, or one or more of the objects along the navigation.

11. The system of claim 8 , wherein the one or more sensors are disposed at least on the vehicle or along a path of the navigation to monitor and dynamically update the local factors.

12. The system of claim 8 , wherein the total collision probability with at least one of the objects along the navigation comprises a summation of probabilities of colliding with the objects along the navigation.

13. The system of claim 8 , wherein determining the navigation for the vehicle through at least the part of the environment based at least on the total collision probability with at least one of the objects along the navigation according to the updated probability models comprises:

determining the navigation for the vehicle through at least the part of the environment based at least on:

minimizing the total collision probability with the objects along the navigation according to the updated probability models, and

satisfying one or more constraints comprising at least one of minimizing a trip time, minimizing a trip distance, minimizing a trip cost, limiting energy consumption, or fulfilling a user request.

14. The system of claim 8 , further comprising controlling the vehicle to move according to the determined navigation, wherein the navigation comprises at least one of a route, a moving speed, or a moving direction.

15. A non-transitory computer readable medium comprising instructions that, when executed, cause one or more processors to perform operations comprising:

obtaining a map of an environment comprising a plurality of objects each associated with a probability model, each of the probability models at least describing one or more probability fields of a vehicle colliding with at least one of the plurality of objects;

obtaining, using the vehicle, one or more global factors from one or more data stores;

obtaining, using one or more sensors, one or more local factors;

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 apply to all of the objects, and the local factors apply to a portion of the objects, wherein at least a first global factor has a first degree of influence for a particular object of the plurality of objects, and wherein the first global factor has a second degree of influence for another object of the plurality of objects, the updating including adjusting a rate of decay for at least one of the probability fields of a corresponding probability model of the plurality of probability models;

determining a navigation for the vehicle through at least a part of the environment based at least on a total collision probability of the vehicle with at least one of the plurality of objects along the navigation according to the updated probability models; and

causing, in response to determining the navigation, the navigation of the vehicle through at least the part of the environment.

16. The non-transitory computer readable medium of claim 15 , wherein:

the objects comprise static and dynamic objects, the particular object comprises a particular static object, and the other object comprises a particular dynamic object;

the static objects are substantially stationary with respect to ground; and

the dynamic objects are movable with respect to ground.

17. The non-transitory computer readable medium of claim 15 , wherein:

the one or more global factors comprise at least one of weather, a global traffic condition, a season, a time, or a geographic location of the environment; and

the one or more local factors comprise at least one of a local event, a local traffic a condition, a local road condition, or one or more of the objects along the navigation.

18. The non-transitory computer readable medium of claim 15 , wherein the one or more sensors are disposed at least on the vehicle or along a path of the navigation to monitor and dynamically update the local factors.

19. The non-transitory computer readable medium of claim 15 , wherein the total collision probability with at least one of the objects along the navigation comprises a summation of probabilities of colliding with the objects along the navigation.

20. The non-transitory computer readable medium of claim 15 , wherein determining the navigation for the vehicle through at least the part of the environment based at least on the total collision probability with at least one of the objects along the navigation according to the updated probability models comprises:

determining the navigation for the vehicle through at least the part of the environment based at least on:

minimizing the total collision probability with the objects along the navigation according to the updated probability models, and

satisfying one or more constraints comprising at least one of minimizing a trip time, minimizing a trip distance, minimizing a trip cost, limiting energy consumption, or fulfilling a user request.