Latency compensation in inertial navigation system

1. A method for calculating location of an autonomous driving vehicle (ADV), comprising:

receiving, at a processing device, new global navigation satellite system (GNSS) data that was captured at a first point in time;

identifying a first previously estimated location, from a plurality of previously estimated locations, having a first timestamp that is closest to the first point in time;

identifying a second previously estimated location, from the plurality of previously estimated locations, having a second timestamp that is closest to a current time, wherein the first point in time occurred prior to the current time;

adjusting the new GNSS data based on a difference between the first previously estimated location and the second previously estimated location; and

calculating, based on the adjusted GNSS data, a current estimated location of the ADV.

2. The method of claim 1 , wherein the plurality of previously estimated locations is stored in a first in first out (FIFO) queue, and wherein each of the plurality of previously estimated locations is pushed into the FIFO queue upon calculation.

3. The method of claim 1 , wherein each of the plurality of previously estimated locations is calculated using at least GNSS data and inertial measurement unit (IMU) data, wherein the IMU data is received at a higher frequency than the GNSS data.

4. The method of claim 1 , wherein identifying the first previously estimated location comprises:

calculating a difference between a timestamp of the new GNSS data corresponding to the first point in time and a timestamp of at least one previously estimated location from the plurality of previously estimated locations; and

identifying a smallest difference indicating the first previously estimated location with the first timestamp closest to the timestamp of the new GNSS data corresponding to the first point in time.

5. The method of claim 1 , wherein adjusting the new GNSS data comprises adding the difference to the new GNSS data.

6. The method of claim 1 , wherein location data of the current estimated location comprises at least one of a geographic position of the ADV, a velocity of the ADV, or a heading of the ADV.

7. The method of claim 1 , wherein the plurality of previously estimated locations are calculated using GNSS data and IMU data as an input to a Kalman filter.

8. A data processing system for calculating a location of an autonomous driving vehicle (ADV) comprising:

a processing device; and

a memory coupled to the processing device to store instructions, which when executed by the processing device, cause the processing device to perform operations, the operations comprising:

receiving new global navigation satellite system (GNSS) data that was captured at a first point in time;

identifying a first previously estimated location, from a plurality of previously estimated locations, having a first timestamp that is closest to the first point in time;

identifying a second previously estimated location, from the plurality of previously estimated locations, having a second timestamp that is closest to a current time, wherein the first point in time occurred prior to the current time;

adjusting the new GNSS data based on a difference between the first previously estimated location and the second previously estimated location; and

calculating, based on the adjusted GNSS data, a current estimated location of the ADV.

9. The system of claim 8 , wherein the plurality of previously estimated locations is stored in a first in first out (FIFO) queue, and wherein each of the plurality of previously estimated locations is pushed into the FIFO queue upon calculation.

10. The system of claim 8 , wherein each of the plurality of previously estimated locations is calculated using at least GNSS data and inertial measurement unit (IMU) data, wherein the IMU data is received at a higher frequency than the GNSS data.

11. The system of claim 8 , wherein identifying the first previously estimated location comprises:

calculating a difference between a timestamp of the new GNSS data corresponding to the first point in time and a timestamp of at least one previously estimated location from the plurality of previously estimated locations; and

identifying a smallest difference indicating the first previously estimated location with a the first timestamp closest to the timestamp of the new GNSS data corresponding to the first point in time.

12. The system of claim 8 , wherein adjusting the new GNSS data comprises adding the difference to the new GNSS data.

13. The system of claim 8 , wherein location data of the current estimated location comprises at least one of a geographic position of the ADV, a velocity of the ADV, or a heading of the ADV.

14. The system of claim 8 , wherein the plurality of previously estimated locations are calculated using GNSS data and IMU data as an input to a Kalman filter.

15. A non-transitory machine-readable medium having instructions stored therein, which when executed by a processor, cause the processor to perform operations to calculate a location of an autonomous driving vehicle (ADV), the operations comprising:

receiving new global navigation satellite system (GNSS) data that was captured at a first point in time;

identifying a first previously estimated location, from a plurality of previously estimated locations, having a first timestamp that is closest to the first point in time;

identifying a second previously estimated location, from the plurality of previously estimated locations, having a second timestamp that is closest to a current time, wherein the first point in time occurred prior to the current time;

adjusting the new GNSS data based on a difference between the first previously estimated location and the second previously estimated location; and

calculating, based on the adjusted GNSS data, a current estimated location of the ADV.

16. The machine-readable medium of claim 15 , wherein the plurality of previously estimated locations is stored in a first in first out (FIFO) queue, and wherein each of the plurality of previously estimated locations is pushed into the FIFO queue upon calculation.

17. The machine-readable medium of claim 15 , wherein each of the plurality of previously estimated locations is calculated using at least GNSS data and inertial measurement unit (IMU) data, wherein the IMU data is received at a higher frequency than the GNSS data.

18. The machine-readable medium of claim 15 , wherein identifying the first previously estimated location comprises:

calculating a difference between a timestamp of the new GNSS data corresponding to the first point in time and a timestamp of at least one previously estimated location from the plurality of previously estimated locations; and

identifying a smallest difference indicating the first previously estimated location with the first timestamp closest to the timestamp of the new GNSS data corresponding to the first point in time.

19. The machine-readable medium of claim 15 , wherein adjusting the new GNSS data comprises adding the difference to the new GNSS data.

20. The machine-readable medium of claim 15 , wherein location data of the current estimated location comprises at least one of a geographic position of the ADV, a velocity of the ADV, or a heading of the ADV.