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, by one or more processors, a vehicle according to a first control strategy;detecting, by the one or more processors, an object at a location external to the vehicle using one or more sensors;predicting, by the one or more processors, a future behavior of the dete

1. A method comprising: controlling, by one or more processors, a vehicle according to a first control strategy;detecting, by the one or more processors, an object at a location external to the vehicle using one or more sensors;predicting, by the one or more processors, a future behavior of the detected object based on the detected location of the object, a time when the object was detected, and behavior data that indicates how other objects have operated at the detected location at a similar time; andmodifying, by the one or more processors, the first control strategy to obtain a second control strategy for controlling the vehicle based on the predicted future behavior of the detected object. 2. The method of claim 1, further comprising: using the detected location to determine a state of the object, andwherein the determined state of the object is used to further predict the future behavior. 3. he method of claim 2, wherein the determined state relates to at least one of: 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. 4. 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 that are contextually similar to the detected location. 5. The method of claim 1, wherein: 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 a classification of the detected object. 6. 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. 7. The method of claim 1, further comprising: receiving updated behavior data from a remote server computer, andwherein predicting the future behavior of the detected object is based at least in part on the updated behavior data. 8. A system comprising one or more processors configured to: control a vehicle according to a first control strategy;detect an object at a location external to the vehicle using one or more sensors;predict a future behavior of the detected object based on the detected location of the object, a time when the object was detected, and behavior data that indicates how other objects have operated at the detected location at a similar time; andmodify the first control strategy to obtain a second control strategy for controlling the vehicle based on the predicted future behavior of the detected object. 9. The system of claim 8, wherein the one or more processors are further configured to: use the detected location to determine a state of the object, andwherein the determined state of the object is used to further predict the future behavior. 10. The system of claim 9, wherein the determined state relates to at least one of: 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. 11. The system of claim 8, wherein the behavior data is based on movement data for a plurality of other objects at one or more locations that are contextually similar to the detected location. 12. The system of claim 8, wherein: 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 a classification of the detected object. 13. The system of claim 8, wherein the likely behavior of the detected object is provided as a probability of the detected object entering to one or more states. 14. The method of claim 1, further comprising: receiving updated behavior data from a remote server computer, andwherein predicting the future behavior of the detected object is based at least in part on the updated behavior data. 15. A non-transitory, tangible computer-readable storage medium on which computer readable instructions of a program are stored, the instructions, when executed by a processor, cause the processor to perform a method, the method comprising: controlling a vehicle according to a first control strategy;detecting an object at a location external to the vehicle using one or more sensors;predicting a future behavior of the detected object based on the detected location of the object, a time when the object was detected, and behavior data that indicates how other objects have operated at the detected location at a similar time; andmodifying the first control strategy to obtain a second control strategy for controlling the vehicle based on the predicted future behavior of the detected object. 16. The medium of claim 15, wherein the method further comprises: using the detected location to determine a state of the object, andwherein the determined state of the object is used to further predict the future behavior. 17. The medium of claim 16, wherein the determined state relates to at least one of: 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. 18. The medium of claim 15, wherein the behavior data is based on movement data for a plurality of other objects at one or more locations that are contextually similar to the detected location. 19. The medium of claim 15, wherein the likely behavior of the detected object is provided as a probability of the detected object entering to one or more states. 20. The medium of claim 15, wherein the method further comprises: receiving updated behavior data from a remote server computer, andwherein predicting the future behavior of the detected object is based at least in part on the updated behavior data.