Method and system for personalized driving lane planning in autonomous driving vehicles
The present teaching relates to method, system, medium, and implementation of lane planning in an autonomous vehicle. Sensor data are received that capture ground images of a road the autonomous vehicle is on. Based on the sensor data, a current lane of the road that autonomous vehicle is currently occupying is detected. Information indicating presence of a passenger in the vehicle is obtained and used to retrieve a personalized lane control model related to the passenger. Lane control for the autonomous vehicle is planned based on the detected current lane and self-aware capability parameters in accordance with the personalized lane control model. The self-aware capability parameters are used to predict operational capability of the autonomous vehicle with respect to a current location of the autonomous vehicle. The personalized lane control model is generated based on recorded human driving data.
1. A method, comprising:
receiving, via a processor, a first set of images generated from real time visual sensor data and depicting a ground surface on which an autonomous vehicle is positioned;
detecting, in real time and based on the first set of images, marks on the ground surface representing a lane that the autonomous vehicle is currently occupying based on at least one lane detection model obtained via machine learning;
receiving, via the processor, data representing a presence of a passenger within the autonomous vehicle;
selecting a personalized lane control model from a plurality of personalized lane control models related to the passenger, each personalized lane control model from the plurality of personalized lane control models being trained via machine learning based on recorded human driving data related to the passenger under different driving conditions;
generating a planned lane control for the autonomous vehicle based on the lane that the autonomous vehicle is currently occupying and self-aware capability parameters associated with the selected personalized lane control model, the generating the planned lane control including using the self-aware capability parameters to predict an operational capability of the autonomous vehicle with respect to a current location of the autonomous vehicle; and
sending a signal to cause implementation of the planned lane control at the autonomous vehicle.
2. The method of claim 1 , wherein the planned lane control includes at least one of lane following or lane changing.
3. The method of claim 1 , wherein the self-aware capability parameters include intrinsic capability parameters and extrinsic capability parameters, the intrinsic capability parameters specifying conditions internal to the autonomous vehicle that limit the operational capability of the autonomous vehicle, the extrinsic capability parameters specifying conditions external to the autonomous vehicle that impact the operational capability of the autonomous vehicle.
4. The method of claim 1 , wherein the self-aware capability parameters are dynamically updated to reflect a scenario the autonomous vehicle is currently associated with.
5. The method of claim 1 , wherein the lane detection model is selected from a plurality of lane detection models based on the self-aware capability parameters.
6. The method of claim 1 , wherein the data representing the presence of the passenger within the autonomous vehicle is obtained by:
receiving a second set of images generated from the real time visual sensor data and depicting an internal scene of the autonomous vehicle;
analyzing the second set of images to detect the presence of the passenger; and
generating the data representing the presence of the passenger within the autonomous vehicle.
7. A non-transitory, processor-readable medium storing instructions to cause a processor to:
receive a first set of images generated from real time visual sensor data and depicting a ground surface on which an autonomous vehicle is positioned;
detect, in real time and based on the first set of images, marks on the ground surface representing a lane that the autonomous vehicle is currently occupying based on at least one lane detection model obtained via machine learning;
receive data representing a presence of a passenger within the autonomous vehicle;
select a personalized lane control model from a plurality of personalized lane control models related to the passenger, wherein each personalized lane control model from the plurality of personalized lane control models is trained via machine learning based on recorded human driving data related to the passenger under different driving conditions;
generate a planned lane control for the autonomous vehicle based on the lane that the autonomous vehicle is currently occupying and self-aware capability parameters associated with the selected personalized lane control model, the generating the planned lane control including using the self-aware capability parameters to predict an operational capability of the autonomous vehicle with respect to a current location of the autonomous vehicle; and
send a signal to cause implementation of the planned lane control at the autonomous vehicle.
8. The medium of claim 7 , wherein the planned lane control includes at least one of lane following or lane changing.
9. The medium of claim 7 , wherein the self-aware capability parameters include intrinsic capability parameters and extrinsic capability parameters, the intrinsic capability parameters specifying conditions internal to the autonomous vehicle that limit the operational capability of the autonomous vehicle, the extrinsic capability parameters specifying conditions external to the autonomous vehicle that impact the operational capability of the autonomous vehicle.
10. The medium of claim 7 , wherein the self-aware capability parameters are dynamically updated to reflect a scenario the autonomous vehicle is currently associated with.
11. The medium of claim 7 , wherein the lane detection model is selected from a plurality of lane detection models based on the self-aware capability parameters.
12. The medium of claim 7 , wherein the data representing the presence of the passenger within the autonomous vehicle is obtained by:
receiving a second set of images generated from the real time visual sensor data and depicting an internal scene of the autonomous vehicle;
analyzing the second set of images to detect the presence of the passenger; and
generating the data representing the presence of the passenger within the autonomous vehicle.
13. A system, comprising:
a driving lane detector implemented by a processor and configured to:
receive a first set of images generated from real time visual sensor data and depicting a ground surface on which an autonomous vehicle is positioned,
detect, in real time and based on the first set of images, marks on the ground surface representing a lane that the autonomous vehicle is currently occupying based on at least one lane detection model obtained via machine learning; and
a driving lane planning unit implemented by the processor and configured to
receive data representing a presence of a passenger within the autonomous vehicle,
select a personalized lane control model from a plurality of personalized lane control models related to the passenger, wherein each personalized lane control model from the plurality of personalized lane control models is trained via machine learning based on recorded human driving data related to the passenger under different driving conditions,
generate a planned lane control for the autonomous vehicle based on the lane that the autonomous vehicle is currently occupying and self-aware capability parameters associated with the selected personalized lane control model, the generating the planned lane control including using the self-aware capability parameters to predict an operational capability of the autonomous vehicle with respect to a current location of the autonomous vehicle; and
send a signal to cause implementation of the planned lane control at the autonomous vehicle.
14. The system of claim 13 , wherein the planned lane includes at least one of lane following or lane changing.
15. The system of claim 13 , wherein the self-aware capability parameters include intrinsic capability parameters and extrinsic capability parameters, the intrinsic capability parameters specifying conditions internal to the autonomous vehicle that limit the operational capability of the autonomous vehicle, the extrinsic capability parameters specifying conditions external to the autonomous vehicle that impact the operational capability of the autonomous vehicle.
16. The system of claim 13 , wherein the self-aware capability parameters are dynamically updated to reflect a scenario the autonomous vehicle is currently associated with.
17. The system of claim 13 , wherein the lane detection model is selected from a plurality of lane detection models based on the self-aware capability parameters.
18. The system of claim 13 , wherein the data representing the presence of the passenger within the autonomous vehicle is obtained by:
receiving a second set of images generated from the real time visual sensor data and depicting an internal scene of the autonomous vehicle;
analyzing the second set of images to detect the presence of the passenger; and
generating the data representing the presence of the passenger within the autonomous vehicle.