Scenario aware perception system for an automated vehicle
A scenario aware perception system ( 10 ) suitable for use on an automated vehicle includes a traffic-scenario detector ( 14 ), an object-detection device ( 24 ), and a controller ( 32 ). The traffic-scenario detector ( 14 ) is used to detect a present-scenario ( 16 ) experienced by a host-vehicle ( 12 ). The object-detection device ( 24 ) is used to detect an object ( 26 ) proximate to the host-vehicle ( 12 ). The controller ( 32 ) is in communication with the traffic-scenario detector ( 14 ) and the object-detection device ( 24 ). The controller ( 32 ) configured to determine a preferred-algorithm ( 36 ) used to identify the object ( 26 ). The preferred-algorithm ( 36 ) is determined based on the present-scenario ( 16 ).
1. A method for controlling an autonomous vehicle, comprising:
determining a present traffic scenario of a plurality of possible traffic scenarios of the autonomous vehicle, wherein each possible traffic scenario characterizes a configuration of a roadway;
selecting a respective object identification algorithm associated with the present traffic scenario, wherein the selected object identification algorithm identifies target objects that move in an expected direction of travel on the roadway characterized by the present traffic scenario; and
identifying one or more target objects proximate to the autonomous vehicle using the selected object identification algorithm, comprising identifying motion of the one or more target objects in accordance with the expected direction of travel of the target objects characterized by the present traffic scenario.
2. The method of claim 1 , wherein identifying one or more target objects proximate to the autonomous vehicle using the selected object identification algorithm comprises:
receiving a radar reflection pattern of the one or more target objects;
comparing the radar reflection pattern of the one or more target objects to a plurality of stored reflection patterns associated with the selected object identification algorithm; and
identifying the one or more target objects based on the comparison.
3. The method of claim 1 , wherein determining the present traffic scenario of the autonomous vehicle comprises:
receiving coordinates defining a location of the autonomous vehicle;
determining a configuration of a roadway at the location of the autonomous vehicle using map data; and
based on the configuration of the roadway at the location, determining the present traffic scenario.
4. The method of claim 1 , wherein determining the present traffic scenario of the autonomous vehicle comprises:
using sensor data to determine the configuration of a roadway at a location of autonomous vehicle; and
based on the configuration of the roadway, determining the present traffic scenario.
5. The method of claim 1 , wherein the present traffic scenario is a four-way stop intersection, a residential roadway, or a roundabout.
6. The method of claim 1 , wherein the traffic scenario is a multilane expressway, and wherein the selected object identification algorithm tracks target vehicles that are parallel to and offset from a travel direction of the autonomous vehicle.
7. The method of claim 1 , wherein the traffic scenario is a two-lane road with an entrance ramp, and wherein the selected object identification algorithm tracks target vehicles that are beside but not parallel to a travel direction of the autonomous vehicle.
8. An autonomous vehicle comprising:
a traffic scenario detector configured to determine a present traffic scenario of a plurality of possible traffic scenarios of the autonomous vehicle, wherein each possible traffic scenario characterizes a configuration of a roadway;
a controller configured to select a respective object identification algorithm associated with the present traffic scenario, wherein the selected object identification algorithm identifies target objects that move in an expected direction of travel on the roadway characterized by the present traffic scenario; and
an object detection device configured to identify one or more target objects proximate to the autonomous vehicle using the selected object identification algorithm and to identify motion of the one or more target objects in accordance with the expected direction of travel of the target objects characterized by the present traffic scenario.
9. The autonomous vehicle of claim 8 , wherein identifying, by the object detection device, one or more target objects proximate to the autonomous vehicle using the selected object identification algorithm comprises:
receiving a radar reflection pattern of the one or more target objects;
comparing the radar reflection pattern of the one or more target objects to a plurality of stored reflection patterns associated with the selected object identification algorithm; and
identifying the one or more target objects based on the comparison.
10. The autonomous vehicle of claim 8 , wherein determining the present traffic scenario of the autonomous vehicle by the traffic scenario detector comprises:
receiving coordinates defining a location of the autonomous vehicle;
determining a configuration of a roadway at the location of the autonomous vehicle using map data; and
based on the configuration of the roadway at the location, determining the present traffic scenario.
11. The autonomous vehicle of claim 8 , wherein determining the present traffic scenario of the autonomous vehicle by the traffic scenario detector comprises:
using sensor data to determine the configuration of a roadway at a location of autonomous vehicle; and
based on the configuration of the roadway, determining the present traffic scenario.
12. The autonomous vehicle of claim 8 , wherein the present traffic scenario is a four-way stop intersection, a residential roadway, or a roundabout.
13. The autonomous vehicle of claim 8 , wherein the traffic scenario is a multilane expressway, and wherein the selected object identification algorithm is used to track target vehicles that are parallel to and offset from a travel direction of the autonomous vehicle.
14. The autonomous vehicle of claim 8 , wherein the traffic scenario is a two-lane road with an entrance ramp, and wherein the selected object identification algorithm is used to track target vehicles that are beside but not parallel to a travel direction of the autonomous vehicle.
15. One or more non-transitory computer storage media storing instructions that are operable, when executed by one or more computers, to cause the one or more computers to perform operations comprising:
determining a present traffic scenario of a plurality of possible traffic scenarios of an autonomous vehicle, wherein each possible traffic scenario characterizes a configuration of a roadway;
selecting a respective object identification algorithm associated with the present traffic scenario, wherein the selected object identification algorithm identifies target objects that move in an expected direction of travel on the roadway characterized by the present traffic scenario; and
identifying one or more target objects proximate to the autonomous vehicle using the selected object identification algorithm, comprising identifying motion of the one or more target objects in accordance with the expected direction of travel of the target objects characterized by the present traffic scenario.