Automated system and method for modeling the behavior of vehicles and other agents
A method and apparatus are provided for determining one or more behavior models used by an autonomous vehicle to predict the behavior of detected objects. The autonomous vehicle may collect and record object behavior using one or more sensors. The autonomous vehicle may then communicate the recorded object behavior to a server operative to determine the behavior models. The server may determine the behavior models according to a given object classification, actions of interest performed by the object, and the object's perceived surroundings.
1. A method of maneuvering a vehicle, the method comprising:
receiving, by one or more processors, object data, wherein the object data comprises a location of an object in an environment of the vehicle;
identifying, from the object data, a classification of the object;
identifying a behavior of interest corresponding to an action taken by the object based on the object data and on map information identifying a road element corresponding to the location of the object;
retrieving from memory, a behavior model for objects configured to predict how another object, having the same classification as the object, will behave based on the classification; and
maneuvering the vehicle, by the one or more processors, based on the behavior model and the identified behavior of interest,
wherein the object data further includes movement information for the object and identifying the behavior of interest is further based on a comparison between the road element and the movement information and the comparison indicates that the object has performed the behavior of interest.
2. The method of claim 1 , wherein the road element comprise a first lane of traffic, and wherein the action taken indicates that the object has changed from a second lane of traffic to the first lane of traffic.
3. The method of claim 1 , wherein the classification corresponds to a road vehicle.
4. The method of claim 1 , wherein the classification corresponds to a pedestrian.
5. The method of claim 1 , wherein the behavior model includes paths of travel for one or more previously monitored objects, and the method further comprises:
using the behavior model to identify a plurality of probabilities for potential actions of the object, and
wherein maneuvering the vehicle includes avoiding a trajectory for at least one of the potential actions.
6. The method of claim 5 , further comprising updating the behavior model by adjusting the plurality of probabilities based on the behavior of interest.
7. The method of claim 1 , further comprising creating, by the one or more processors, an initial behavior model for the object based on the object data and the map information, when a behavior model does not exist for a classification for the object.
8. The method of claim 1 , wherein the behavior model provides information based on weather conditions.
9. A system for maneuvering a vehicle, the system comprising one or more processors configured to:
receive object data, wherein the object data comprises a location of an object in an environment of the vehicle;
identify, from the object data, a classification of the object;
identify a behavior of interest corresponding to an action taken by the object based on the object data and on map information identifying a road element corresponding to the location of the object;
retrieve from memory, a behavior model for objects configured to predict how another object, having the same classification as the object, will behave based on the classification; and
maneuver the vehicle based on the behavior model and the identified behavior of interest,
wherein the object data further includes movement information for the object, and the one or more processors are further configured to identify the behavior of interest further based on a comparison between the road element and the movement information and the comparison indicates that the object has performed the behavior of interest.
10. The system of claim 9 , further comprising the vehicle.
11. The system of claim 9 , further comprising the memory, and wherein the memory further stores the map information.
12. The system of claim 9 , wherein the road element comprise a first lane of traffic, and wherein the action taken indicates that the object has changed from a second lane of traffic to the first lane of traffic.
13. The system of claim 9 , wherein the classification corresponds to a road vehicle.
14. The system of claim 9 , wherein the classification corresponds to a pedestrian.
15. The system of claim 9 , wherein the behavior model includes paths of travel for one or more previously monitored objects, and the one or more processors are further configured to:
use the behavior model to identify a plurality of probabilities for potential actions of the object, and
to maneuver the vehicle by avoiding a trajectory for at least one of the potential actions.
16. The system of claim 15 , wherein the one or more processors are further configured to update the behavior model by adjusting the plurality of probabilities based on the behavior of interest.
17. The system of claim 9 , further comprising creating an initial behavior model for the object based on the object data and the map information, when a behavior model does not exist for a classification for the object.
18. The system of claim 9 , wherein the behavior model provides information based on weather conditions.
19. A non-transitory, computer readable recording 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 of maneuvering a vehicle, the method comprising:
receiving object data, wherein the object data comprises a location of an object in an environment of the vehicle;
identifying, from the object data, a classification of the object;
identifying a behavior of interest corresponding to an action taken by the object based on the object data and on map information identifying a road element corresponding to the location of the object;
retrieving from memory, a behavior model for objects configured to predict how another object, having the same classification as the object, will behave based on the classification; and
maneuvering the vehicle based on the behavior model and the identified behavior of interest,
wherein the object data further includes movement information for the object and identifying the behavior of interest is further based on a comparison between the road element and the movement information and the comparison indicates that the object has performed the behavior of interest.
20. The medium of claim 18 , further comprising creating an initial behavior model for the object based on the object data and the map information, when a behavior model does not exist for a classification for the object.