Sensor fusion of camera and V2V data for vehicles
A method for fusing sensor information detected by a host vehicle and at least one remote vehicle-to-vehicle (V2V) communication equipped vehicle includes collecting visual data from an optical sensor of a vision sub-system, and collecting V2V data from remote vehicles. The method further includes executing a control logic including a first control logic for generating a base lane model and a base confidence level, a second control logic that fuses together the V2V data, the base lane model, and the base confidence level, and a third control logic that generates from the fused lane model, the V2V data, the base lane model, and the base confidence level, a final lane model and final confidence level, and assigns a priority to the final lane model.
1. A method for fusing sensor information detected by a host vehicle and at least one remote vehicle-to-vehicle (V2V) communication equipped vehicle, the method comprising:
collecting visual data from an optical sensor of a vision sub-system, and generating a base lane model and a base confidence level from the visual data;
collecting V2V data from a receiver of a V2V sub-system;
fusing together the V2V data, the base lane model, and the base confidence level;
generating a final lane model with a final confidence level from the fused together V2V data, the base lane model and the base confidence level;
assigning a priority to the final lane model; and
determining a location of an object in the final lane model relative to the host vehicle and assigning a high priority to the object when the object is in a lane also occupied by the host vehicle, and sending a command to at least one advanced driver assistance system (ADAS), and wherein the at least one ADAS performs a function to avoid the object to which a high priority has been assigned.
2. The method of claim 1 wherein the final confidence level indicates that the final lane model is more accurate than the base lane model.
3. The method of claim 2 wherein the base lane model and the final lane model comprise lane positioning, lane markings, lane curvature, speed, and trajectory data for the host vehicle and for any objects within a predefined area around the host vehicle.
4. The method of claim 3 wherein the V2V data comprises lane positioning, speed, and trajectory data for any remote V2V equipped vehicles in communication with the host vehicle and within a predefined area around the host vehicle, and for any objects sensed by any remote V2V vehicles in communication with the host vehicle and within a predefined area around the host vehicle.
5. The method of claim 1 , wherein the fusing together of the V2V data, the base lane model, and the base confidence level further comprises comparing the visual data to the V2V data and determining a relative accuracy and precision of the visual data and the V2V data.
6. A system for fusing sensor information detected by a host vehicle and at least one remote vehicle-to-vehicle (V2V) communication equipped vehicle, the system comprising:
a vision sub-system having an optical sensor;
a V2V sub-system having a receiver;
a controller in communication with the vision sub-system and the V2V sub-system, the controller having memory for storing control logic and a processor configured to execute the control logic, the control logic including a first control logic for collecting visual data from the vision sub-system, and from the visual data generating a base lane model and a base confidence level;
the processor including a second control logic for collecting V2V data from the V2V sub-system, and for fusing together the V2V data and the base lane model and base confidence level;
the processor including a third control logic for generating, from the fused V2V data, base lane model and base confidence level, a final lane model with a final confidence level;
the processor including a fourth logic for assigning a priority to the final lane model; and
determining a location of an object in the final lane model relative to the host vehicle and assigning a high priority to the object when the object is in a lane also occupied by the host vehicle, wherein information about the object that has been assigned a high priority is passed to the at least one ADAS, and the at least one ADAS performs a function to avoid the object.
7. The system of claim 6 wherein the final confidence level indicates that the final lane model is more accurate than the base lane model.
8. The system of claim 7 wherein the base and the final lane models comprise lane positioning, lane markings, lane curvature, speed, and trajectory data for the host vehicle and for any objects within a predefined area around the host vehicle.
9. The system of claim 8 wherein the V2V data comprises lane positioning, speed, and trajectory data for any remote V2V equipped vehicles in communication with the host vehicle and within a predefined area around the host vehicle, and for any objects sensed by any remote V2V vehicles in communication with the host vehicle and within a predefined area around the host vehicle.
10. The system of claim 6 , wherein the controller fuses together further comprises comparing the visual data to the V2V data and determining an accuracy and a precision of the visual data and the V2V data.