Granted Patent B2

US 12,379,227 · App. 18/117,231 · Granted Aug 5, 2025

Inventors: Xuehe Zheng (Shanghai, CN); Wei Long (Shanghai, CN); Congmin Bai (Shanghai, CN)

Assignee: Telenav, Inc.

G01C21/3889G01C21/32G01C21/3602G06T7/73G01C21/3878G06T2207/10028G06T2207/30252

Abstract

Claims (47)

1. A navigation system comprising:

a control circuit configured to:

capture a semantic frame from a sensor data stream for a region of interest, crop an outer peripheral edge of the semantic frame by removing semantic points beyond the outer peripheral edge,

calculate a world coordinate point cloud by calculating a global positioning system (GPS) location of the semantic points includes a pose error corrected,

establish a probability value for a base-level grid,

generate a semantic grid map by identifying a dominant percentage of the probability value of the base-level grid and an upper-level grid, and

generate a semantic map from the semantic grid map to represent the region of interest; and

a communication circuit, coupled to the control circuit, configured to transmit the semantic map for displaying on a device.

2. The system as claimed in claim 1 wherein the control circuit is configured to calculate an update grid map probability by calculating a log (Probability (s/z)) (EQ3).

3. The system as claimed in claim 1 wherein the control circuit is configured to capture the semantic frame includes:

identify a frame center of the semantic frame; and

calculate a body point cloud location for the semantic point by counting pixels between the frame center and the semantic point.

4. The system as claimed in claim 1 wherein the control circuit is configured to generate the semantic grid map of the semantic points includes generating the upper-level grid with dimensions of H×H meters and the base-level grid with dimensions of L×L centimeters within the upper-level grid.

5. The system as claimed in claim 1 wherein the control circuit is configured to correct the pose error includes calculating the world coordinate of a semantic point observed by more than one of the optical sensors.

6. The system as claimed in claim 1 wherein the control circuit is configured to capture the semantic frame from a sensor data stream includes a front optical sensor, a rear optical sensor, a left side optical sensor, and a right optical sensor provide the sensor data stream.

7. The system as claimed in claim 1 wherein the control circuit is configured to parse the semantic map through the upper-level grid to the base-level grid provides centimeter accuracy on a roadway.

8. A method of operation for a navigation system comprising:

capturing a semantic frame from a sensor data stream for a region of interest;

cropping an outer peripheral edge of the semantic frame by removing semantic points beyond the outer peripheral edge;

calculating a world coordinate point cloud by calculating a global positioning system (GPS) location of the semantic points includes a pose error corrected;

establishing a probability value for a base-level grid;

generating a semantic grid map by identifying a dominant percentage of the probability value of the base-level grid and an upper-level grid;

generating a semantic map from the semantic grid map to represent the region of interest; and

transmitting the semantic map for displaying on a device.

9. The method as claimed in claim 8 further comprising calculating an update grid map probability by calculating a log (Probability (s/z)) (EQ3).

10. The method as claimed in claim 8 wherein capturing a semantic frame includes:

identifying a frame center of the semantic frame; and

calculating a body point cloud location for the semantic point by counting pixels between the frame center and the semantic point.

11. The method as claimed in claim 8 wherein generating the semantic grid map of the semantic points includes generating the upper-level grid with dimensions of H×H meters and the base-level grid with dimensions of L×L centimeters within the upper-level grid.

12. The method as claimed in claim 8 wherein correcting the pose error includes calculating the GPS location of a semantic point observed by more than one of the optical sensors.

13. The method as claimed in claim 8 wherein capturing a semantic frame from a sensor data stream includes a front optical sensor, a rear optical sensor, a left side optical sensor, and a right optical sensor providing the sensor data stream.

14. The method as claimed in claim 8 further comprising parsing the semantic map through the upper-level grid to the base-level grid provides centimeter accuracy on a roadway.

15. A non-transitory computer readable medium including instructions for a navigation system comprising:

capturing a semantic frame from a sensor data stream for a region of interest;

cropping an outer peripheral edge of the semantic frame by removing semantic points beyond the outer peripheral edge;

calculating a world coordinate point cloud by calculating a global positioning system (GPS) location of the semantic points includes a pose error corrected;

establishing a probability value for a base-level grid;

generating a semantic grid map by identifying a dominant percentage of the probability value of the base-level grid and an upper-level grid;

generating a semantic map from the semantic grid map to represent the region of interest; and

transmitting the semantic map for displaying on a device.

16. The non-transitory computer readable medium including the instructions as claimed in claim 15 further comprising calculating an update grid map probability by calculating a log (Probability (s z)) (EQ3).

17. The non-transitory computer readable medium including the instructions as claimed in claim 15 wherein capturing a semantic frame includes:

identifying a frame center of the semantic frame; and

calculating a body point cloud location for the semantic point by counting pixels between the frame center and the semantic point.

18. The non-transitory computer readable medium including the instructions as claimed in claim 15 wherein generating the semantic grid map of the semantic points includes generating the upper-level grid with dimensions of H×H meters and the base-level grid with dimensions of L×L centimeters within the upper-level grid.

19. The non-transitory computer readable medium including the instructions as claimed in claim 15 wherein correcting the pose error includes calculating the GPS location of a semantic point observed by more than one of the optical sensors.

20. The non-transitory computer readable medium including the instructions as claimed in claim 15 further comprising parsing the semantic map through the upper-level grid to the base-level grid provides centimeter accuracy on a roadway.

Assignments (1)

Continuity (1)

References Cited (14)