Method for drifting correction for planning a path for autonomous driving vehicles

1. A computer-implemented method for planning a path to drive an autonomous driving vehicle, the method comprising:

determining a current location of an autonomous driving vehicle (ADV) based on sensor data obtained from a plurality of sensors mounted on the ADV;

planning a path for a current driving cycle to drive the ADV from the current location for a predetermined period of time;

determining an expected location of the ADV that was calculated based on a previous path determined during a previous driving cycle;

calculating a drifting error between the current location and the expected location of the ADV;

calculating a drifting correction factor representing a current drifting correction factor that is calculated based on a prior drifting correction factor determined during the previous driving cycle and the drifting error determined during the current driving cycle;

modifying at least a starting point of the path for the current driving cycle based on the drifting error and the drifting correction factor, generating a modified path; and

controlling the ADV to drive according to the modified path.

2. The method of claim 1 , wherein the drifting error represents a difference between the expected location and the current location of the ADV.

3. The method of claim 1 , further comprising:

calculating the drifting correction factor based on the drifting error using a predetermined drifting correction algorithm; and

modifying at least the starting point of the path based on the drifting correction factor.

4. The method of claim 1 , wherein the current drifting correction factor (y current ) is calculated as follows: y current =y prior +k/time_window_value, and wherein k represents the drifting error and the time_window_value represents a predetermined time window period.

5. The method of claim 4 , wherein the time_window_value is ranging approximately 200 to 400.

6. The method of claim 1 , wherein modifying at least the starting point of the path for the current driving cycle comprises:

projecting the path onto a station-lateral (SL) map as an SL curve, wherein the SL curve represents relative positions of a plurality of path points of the path relative to a reference line of a lane in which the ADV is driving; and

shifting at least the starting point of the SL curve laterally based on the drifting correction factor, wherein the shifted SL curve is utilized to adjust the path.

7. A non-transitory machine-readable medium having instructions stored therein, which when executed by a processor, cause the processor to perform operations of operating an autonomous driving vehicle, the operations comprising:

determining a current location of an autonomous driving vehicle (ADV) based on sensor data obtained from a plurality of sensors mounted on the ADV;

planning a path for a current driving cycle to drive the ADV from the current location for a predetermined period of time;

determining an expected location of the ADV that was calculated based on a previous path determined during a previous driving cycle;

calculating a drifting error between the current location and the expected location of the ADV;

calculating a drifting correction factor representing a current drifting correction factor that is calculated based on a prior drifting correction factor determined during the previous driving cycle and the drifting error determined during the current driving cycle;

modifying at least a starting point of the path for the current driving cycle based on the drifting error and the drifting correction factor, generating a modified path; and

controlling the ADV to drive according to the modified path.

8. The machine-readable medium of claim 7 , wherein the drifting error represents a difference between the expected location and the current location of the ADV.

9. The machine-readable medium of claim 7 , wherein the operations further comprise:

calculating the drifting correction factor based on the drifting error using a predetermined drifting correction algorithm; and

modifying at least the starting point of the path based on the drifting correction factor.

10. The machine-readable medium of claim 7 , wherein the current drifting correction factor (y current ) is calculated as follows: y current =y prior +k/time_window_value, and wherein k represents the drifting error and the time_window_value represents a predetermined time window period.

11. The machine-readable medium of claim 10 , wherein the time_window_value is ranging approximately 200 to 400.

12. The machine-readable medium of claim 7 , wherein modifying at least the starting point of the path for the current driving cycle comprises:

projecting the path onto a station-lateral (SL) map as an SL curve, wherein the SL curve represents relative positions of a plurality of path points of the path relative to a reference line of a lane in which the ADV is driving; and

shifting at least the starting point of the SL curve laterally based on the drifting correction factor, wherein the shifted SL curve is utilized to adjust the path.

13. A data processing system, comprising:

a processor; and

a memory coupled to the processor to store instructions, which when executed by the processor, cause the processor to perform operations, the operations including

determining a current location of an autonomous driving vehicle (ADV) based on sensor data obtained from a plurality of sensors mounted on the ADV,

planning a path for a current driving cycle to drive the ADV from the current location for a predetermined period of time,

determining an expected location of the ADV that was calculated based on a previous path determined during a previous driving cycle,

calculating a drifting error between the current location and the expected location of the ADV,

calculating a drifting correction factor representing a current drifting correction factor that is calculated based on a prior drifting correction factor determined during the previous driving cycle and the drifting error determined during the current driving cycle,

modifying at least a starting point of the path for the current driving cycle based on the drifting error and the drifting correction factor, generating a modified path, and

controlling the ADV to drive according to the modified path.

14. The system of claim 13 , wherein the drifting error represents a difference between the expected location and the current location of the ADV.

15. The system of claim 13 , wherein the operations further comprise:

calculating the drifting correction factor based on the drifting error using a predetermined drifting correction algorithm; and

modifying at least the starting point of the path based on the drifting correction factor.

16. The system of claim 13 , wherein the current drifting correction factor (y current ) is calculated as follows: y current =y prior +k/time_window_value, and wherein k represents the drifting error and the time_window_value represents a predetermined time window period.

17. The system of claim 16 , wherein the time_window_value is ranging approximately 200 to 400.

18. The system of claim 13 , wherein modifying at least the starting point of the path for the current driving cycle comprises:

projecting the path onto a station-lateral (SL) map as an SL curve, wherein the SL curve represents relative positions of a plurality of path points of the path relative to a reference line of a lane in which the ADV is driving; and

shifting at least the starting point of the SL curve laterally based on the drifting correction factor, wherein the shifted SL curve is utilized to adjust the path.