초록 ▼

Aspects of the disclosure relate generally to detecting discrete actions by traveling vehicles. The features described improve the safety, use, driver experience, and performance of autonomously controlled vehicles by performing a behavior analysis on mobile objects in the vicinity of an autonomous

Aspects of the disclosure relate generally to detecting discrete actions by traveling vehicles. The features described improve the safety, use, driver experience, and performance of autonomously controlled vehicles by performing a behavior analysis on mobile objects in the vicinity of an autonomous vehicle. Specifically, an autonomous vehicle is capable of detecting and tracking nearby vehicles and is able to determine when these nearby vehicles have performed actions of interest by comparing their tracked movements with map data.

대표청구항 ▼

1. A method for autonomous control of a vehicle, the method comprising: controlling an autonomous vehicle in accordance with a control strategy;detecting one or more nearby vehicles external to the autonomous vehicle using one or more sensors, wherein the nearby vehicles each have a position, headin

1. A method for autonomous control of a vehicle, the method comprising: controlling an autonomous vehicle in accordance with a control strategy;detecting one or more nearby vehicles external to the autonomous vehicle using one or more sensors, wherein the nearby vehicles each have a position, heading, and speed;accessing map data having a plurality of road graph elements;determining with a processor that a first vehicle from one of the nearby vehicles is traveling on a first road graph element;comparing data representing the at least one of the position, heading and speed for the first vehicle with map data for the first road graph element;determining with a processor, based on the comparison, that the first vehicle from the one or more nearby vehicles has performed an action of interest by traveling from the first road graph element to a second road graph element; andaltering the control strategy for the autonomous vehicle based on the action of interest having been performed by the first vehicle. 2. The method of claim 1, wherein the determining comprises determining that the first vehicle is travelling on a roadway containing a first lane and a second lane, and that the first vehicle has changed from the first lane to the second lane. 3. The method of claim 1, wherein altering the control strategy comprises positioning the autonomous vehicle relative to the first vehicle in a predefined manner based on the occurrence of the action of interest. 4. The method of claim 1, further comprising: determining, based on the comparison, that a second vehicle from the one or more nearby vehicles has performed a second action of interest; andfurther altering the control strategy for the autonomous vehicle based on the second action of interest having been performed by the second vehicle. 5. The method of claim 1, further comprising: receiving a request to navigate between a first location and a second location; andautonomously navigating the autonomous vehicle between the first location and a second location,wherein detecting one or more nearby vehicles and controlling the autonomous vehicle occurs while traveling along a path between the first location and the second location. 6. The method of claim 1, further comprising: determining a relative position of the autonomous vehicle with each of the one or more nearby vehicles, andwherein associating each of the one or more nearby vehicles with a road graph element is based on the relative position. 7. A system for controlling a vehicle having an autonomous operation mode, the system comprising: one or more sensors for detecting a one or more nearby vehicles in an autonomous vehicle's surroundings; anda processor configured to:control the autonomous vehicle in accordance with a control strategy;determine a position, heading, and speed for each of the nearby vehicles;access map data having a plurality of road graph elements on which vehicles are able to travel;associate each of the nearby vehicles with a road graph element;compare data representing the at least one of the position, heading and speed for each of the nearby vehicles with the road graph element;determine, based on the comparison, that a first vehicle from the one or more nearby vehicles has performed an action of interest by traveling from a first road graph element to a second road graph element; andalter the control strategy for the autonomous vehicle based on the action of interest having been performed by the first vehicle. 8. The system of claim 7, wherein the determining by the processor comprises determining that the first vehicle is travelling on a roadway containing a first lane and a second lane, and wherein the processor determines that the first vehicle has performed an action of interest by determining that the first vehicle has traveled from the first lane to the second lane. 9. The system of claim 7, wherein the processor alters the control strategy by positioning the autonomous vehicle relative to the first vehicle in a predefined manner. 10. The system of claim 7, the processor being further configured to: determine, based on the comparison, that a second vehicle from the one or more nearby vehicles has performed a second action of interest; andfurther alter the control strategy for the autonomous vehicle based on the second action of interest having been performed by the second vehicle. 11. The system of claim 7, the processor being further configured to: receive a request to navigate between a first location and a second location; andautonomously navigate the autonomous vehicle between the first location and a second location,wherein detecting the one or more nearby vehicles and controlling the autonomous vehicle occurs while traveling along a path between the first location and the second location. 12. The system of claim 7, the processor being further configured to: determine a relative position of the autonomous vehicle with each of the nearby vehicles;associate each of the nearby vehicles with a road graph element based on the relative position. 13. A method for determining discrete activities of vehicles, the method comprising: detecting a first vehicle using one or more sensors;accessing map data having a plurality of road graph elements;determining with a processor that the first vehicle is traveling on a first road graph element;recording vehicle data representing movement of the first vehicle;comparing the vehicle data with the map data;determining using a processor, based on the comparison, whether the first vehicle's movement corresponds with an action of interest by traveling from the first road graph element to a second road graph element; andfiltering the vehicle data for only data relating to an action of interest. 14. The method of claim 13, further comprising autonomously controlling a second vehicle based on the filtered vehicle data. 15. The method of claim 14, wherein autonomously controlling the second vehicle comprises transitioning from a first control strategy to a second control strategy based on the filtered vehicle data. 16. The method of claim 13, wherein the first vehicle is travelling on a road having at least a first lane of traffic and second lane of traffic, and wherein the first road graph element corresponds to the first lane of traffic. 17. The method of claim 14, wherein the action of interest comprises the first vehicle changing from the first lane to the second lane.