Methods and systems for learning user preferences for lane changes
Systems and methods are provided for controlling a vehicle. In one embodiment, a method includes: storing, in a data storage device, a decision model, wherein the decision model predicts when to automatically perform a motivational lane change; updating, by a processor, the decision model based on data obtained in response to user input; and automatically requesting, by the processor, a lane change based on the dynamically updated model.
1. A method for controlling a vehicle, comprising:
storing, in a data storage device, a decision model, wherein the decision model predicts when to automatically perform a motivational lane change and provides control parameters for controlling the vehicle to perform the motivational lane change, wherein the motivational lane change is a lane change that is based on a user's preference to pass another vehicle or object;
updating, by a processor, the decision model based on data obtained in response to user input indicating user preferences associated with lane changes; and
automatically requesting, by the processor, a lane change based on the updated model.
2. The method of claim 1 , wherein the updating is based on user input received directly from a user of the vehicle through a human machine interface.
3. The method of claim 2 , wherein the user input includes positive feedback received in response to a system request to perform a lane change.
4. The method of claim 2 , wherein the user input includes negative feedback received in response to a system request to perform a lane change.
5. The method of claim 3 , wherein the user input includes a user initiated request to perform a lane change when the system request to perform the lane change is not presented to the user.
6. The method of claim 1 , wherein the updating is based on user input received indirectly from a user of the vehicle when the user is navigating the vehicle.
7. The method of claim 1 , wherein the data includes vehicle behavior data, object data, environment data, road structure data, schedule data, sensor confidence data, and user profile data.
8. A system for controlling a vehicle, comprising:
a first data storage device that stores data defining a decision model, wherein the decision model predicts when to automatically perform a motivational lane change, wherein the decision model provides control parameters for controlling the vehicle to perform the lane change, wherein the motivational lane change is a lane change that is based on a user's preference to pass another vehicle or object; and
a processor configured to:
update the decision model based on data obtained in response to user input indicating user preferences associated with lane changes; and
automatically request a lane change based on the updated model.
9. The system of claim 8 , wherein the processor updates based on user input received directly from a user of the vehicle through a human machine interface.
10. The system of claim 9 , wherein the user input includes positive feedback received in response to a system request to perform a lane change.
11. The system of claim 9 , wherein the user input includes negative feedback received in response to a system request to perform a lane change.
12. The system of claim 10 , wherein the user input includes a user initiated request to perform a lane change when the system request to perform the lane change is not presented to the user.
13. The system of claim 8 , wherein the processor updates based on user input received indirectly from a user of the vehicle when the user is navigating the vehicle.
14. The system of claim 8 , wherein the data includes vehicle behavior data, object data, environment data, road structure data, schedule data, sensor confidence data, and user profile data.
15. The system of claim 8 , wherein the decision model includes a decision tree.
16. The system of claim 8 , wherein the decision model includes a random forest.