초록

Aspects of the invention relate generally to autonomous vehicles. Specifically, the features described may be used alone or in combination in order to improve the safety, use, driver experience, and performance of these vehicles.

대표청구항 ▼

1. A method comprising: controlling a vehicle according to a first control strategy, the first control strategy determined based on a route to a destination;detecting an object external to the vehicle using one or more sensors;using a processor, determining a classification and a state of the detect

1. A method comprising: controlling a vehicle according to a first control strategy, the first control strategy determined based on a route to a destination;detecting an object external to the vehicle using one or more sensors;using a processor, determining a classification and a state of the detected object;determining a current location of the vehicle;accessing behavior data for other objects having the same or similar classifications and states as the detected object, the behavior data indicating how the other objects have operated at the current location at one or more previous times;predicting a likely behavior of the detected object at the current location based on the behavior data for the other objects having the same or similar classification and state as the detected object; andmodifying the first control strategy to obtain a second control strategy for controlling the vehicle based on the predicted likely behavior of the detected object. 2. The method of claim 1, wherein the classification of the detected object includes one of an automobile, a pedestrian, structure, or a bicycle. 3. The method of claim 1, wherein the detected object is an automobile, and wherein the classification of the detected object includes the type of automobile. 4. The method of claim 1, wherein the determining a classification of the detected object is based on identifying at least one of a logo, a bumper sticker, or a license plate. 5. The method of claim 1, wherein the state of the detected object relates to at least one of: location, traffic lane in which the detected object is traveling, speed, acceleration, entry onto a road, exit off of a road, activation of headlights, activation of taillights, or activation of blinkers. 6. The method of claim 1, wherein the behavior data is based on movement data for a plurality of other objects at one or more locations. 7. The method of claim 6, wherein the movement data are tracked using one of: satellite imagery, roadside cameras, on-board GPS data, or sensor data acquired for other nearby vehicles. 8. The method of claim 1, wherein: implementing the second control strategy comprises providing a command to orient the vehicle in a position and velocity based at least in part on the likely behavior of the detected object; andproviding the command to orient the vehicle includes positioning the vehicle at a predetermined distance from the detected object, the predetermined distance being based, at least in part, on the classification of the detected object. 9. The method of claim 1, wherein the likely behavior of the detected object is provided as a probability of the detected object entering to one or more states. 10. The method of claim 1, further comprising: receiving updated behavior data; andwherein predicting the likely behavior of the detected object is based at least in part on the updated behavior data. 11. The method of claim 10, wherein receiving the updated behavior data comprises accessing a remote server. 12. A system comprising: one or more sensors for detecting an object in a vehicle's surroundings; anda processor coupled to the one or more sensors, the processor being operable to: control operation of the vehicle based on a first control strategy, wherein the first control strategy is determined based on a route to a destination;determine a classification and a state of a detected object;determine a current location of the vehicle;access behavior data for other objects having the same or similar classifications and states similar as the detected object, the behavior data indicating how the other objects have operated at the current location at one or more previous times;predict a likely behavior of the detected object at the current location based on the behavior data for the other objects having the same or similar classification and state as the detected object; andmodify the first control strategy to obtain a second control strategy for controlling the vehicle based on the predicted likely behavior of the detected object. 13. The system of claim 12, wherein the classification of the detected object includes classifying the detected object as one of: an automobile, a pedestrian, a bicycle, or a structure. 14. The system of claim 12, wherein the detected object is an automobile, and wherein the classification of the detected object includes identifying the type of automobile. 15. The system of claim 12, wherein the classification of the detected object is based on at least one of: a logo, a bumper sticker, or a license plate. 16. The system of claim 12, wherein the state of the detected object relates to at least one of: location, traffic lane in which the detected object is traveling, speed, acceleration, entry onto a road, exit off of a road, activation of headlights, activation of taillights, or activation of blinkers. 17. The system of claim 12, wherein the behavior data represents information regarding the states of the other objects that have been tracked at one or more locations. 18. The system of claim 17, wherein the objects have been tracked using at least one of: satellite imagery, roadside cameras, on-board GPS data, or via sensor data acquired from other nearby entities. 19. The system of claim 12, wherein the second control strategy includes positioning the vehicle at a predetermined distance from the detected object, the predetermined distance being based, at least in part, on the classification of the detected object. 20. The system of claim 12, wherein the likely behavior of the detected object is provided as a probability of the detected object entering to one or more states. 21. The system of claim 12, wherein the processor is further operable to access updated behavior data; andwherein the likely behavior of the detected object is based at least in part on the updated behavior data. 22. The system of claim 21, wherein the vehicle receives the updated behavior data from a remote server. 23. A method for providing data in connection with controlling of a vehicle, the method comprising: storing, at a server, behavior data for a plurality of objects, wherein the behavior data includes classification and state information for at least a subset of the plurality of objects at one or more locations and at one or more times;receiving identification data from a remote device, wherein the identification data includes data relating to a detected object near the remote device;receiving a location of the detected object;determining, at the server, the classification and state of the detected object;predicting a likely behavior of the detected object based on the behavior data for the plurality of objects having a classification and state similar to the detected object for the location where the detected object was detected and the time when the detected object was detected;transmitting the likely behavior of the detected object to the remote device.