System for sensor synchronization data analysis in an autonomous driving vehicle
The disclosure describes various embodiments for online system-level validation of sensor synchronization. According to an embodiment, an exemplary method of analyzing sensor synchronization in an autonomous driving vehicle (ADV) include the operations of acquiring raw sensor data from a first sensor and a second sensor mounted on the ADV, the raw sensor data describing a target object in a surrounding environment of the ADV; and generating an accuracy map based on the raw sensor data in view of timestamps extracted from the raw sensor data. The method further includes the operations of generating a first bounding box and a second bounding box around the target object using the raw sensor data; and performing an analysis of the first and second bounding boxes and the accuracy map using a predetermined algorithm in view of one or more pre-configured sensor settings to determine whether the first sensor and the second sensor are synchronized with each other.
1. A computer-implemented method of analyzing sensor synchronization in an autonomous driving vehicle (ADV), comprising:
acquiring raw sensor data from a first sensor and a second sensor mounted on the ADV, the raw sensor data describing a target object in a surrounding environment of the ADV;
generating an accuracy map based on the raw sensor data and timestamps extracted from the raw sensor data;
generating a first bounding box and a second bounding box around the target object using the raw sensor data; and
performing an analysis of the first and second bounding boxes and the accuracy map using a predetermined algorithm in view of one or more pre-configured sensor settings to determine whether the first sensor and the second sensor are synchronized with each other.
2. The method of claim 1 , wherein the first sensor is a camera and the second sensor is a light detection and ranging (LiDAR) device.
3. The method of claim 2 , wherein the one or more pre-configured sensor settings include a scan direction for the camera and a scan direction for the LiDAR device.
4. The method of claim 2 , wherein performing the analysis further comprises:
determining whether a first piece of raw sensor data from the camera and a second piece of raw sensor data from the LiDAR device align with each other at a pre-determined synchronization point in view of their respective acquisition timestamps.
5. The method of claim 4 , wherein the synchronization point is determined based on a type of the target object.
6. The method of claim 2 , wherein the first bounding box is a 2-D bounding box generated based on a first piece of sensor data from the camera, and wherein the second bounding box is a 3-D bounding box generated based on a second piece of sensor data from the LiDAR device.
7. The method of claim 2 , wherein performing the analysis further comprises:
determining whether the first bounding box and the second bounding box match each other.
8. A non-transitory machine-readable medium having instructions stored therein, which when executed by a processor, cause the processor to perform operations, the operations comprising:
acquiring raw sensor data from a first sensor and a second sensor mounted on an ADV, the raw sensor data describing a target object in a surrounding environment of the ADV;
generating an accuracy map based on the raw sensor data in view of timestamps extracted from the raw sensor data;
generating a first bounding box and a second bounding box around the target object using the raw sensor data; and
performing an analysis of the first and second bounding boxes and the accuracy map using a predetermined algorithm in view of one or more pre-configured sensor settings to determine whether the first sensor and the second sensor are synchronized with each other.
9. The non-transitory machine-readable medium of claim 8 , wherein the first sensor is a camera and the second sensor is a light detection and ranging (LiDAR) device.
10. The non-transitory machine-readable medium of claim 9 , wherein the one or more pre-configured sensor settings include a scan direction for the camera and a scan direction for the LiDAR device.
11. The non-transitory machine-readable medium of claim 9 , wherein performing the analysis further comprises:
determining whether a first piece of raw sensor data from the camera and a second piece of raw sensor data from the LiDAR device align with each other at a pre-determined synchronization point in view of their respective acquisition timestamps.
12. The non-transitory machine-readable medium of claim 11 , wherein the synchronization point is determined based on a type of the target object.
13. The non-transitory machine-readable medium of claim 9 , wherein the first bounding box is a 2-D bounding box generated based on a first piece of sensor data from the camera, and wherein the second bounding box is a 3-D bounding box generated based on a second piece of sensor data from the LiDAR device.
14. The non-transitory machine-readable medium of claim 9 , wherein performing the analysis further comprises:
determining whether the first bounding box and the second bounding box match each other.
15. 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
acquiring raw sensor data from a first sensor and a second sensor mounted on an ADV, the raw sensor data describing a target object in a surrounding environment of the ADV;
generating an accuracy map based on the raw sensor data in view of timestamps extracted from the raw sensor data;
generating a first bounding box and a second bounding box around the target object using the raw sensor data; and
performing an analysis of the first and second bounding boxes and the accuracy map using a predetermined algorithm in view of one or more pre-configured sensor settings to determine whether the first sensor and the second sensor are synchronized with each other.
16. The system of claim 15 , wherein the first sensor is a camera and the second sensor is a light detection and ranging (LiDAR) device.
17. The system of claim 16 , wherein the one or more pre-configured sensor settings include a scan direction for the camera and a scan direction for the LiDAR device.
18. The system of claim 16 , wherein performing the analysis further comprises:
determining whether a first piece of raw sensor data from the camera and a second piece of raw sensor data from the LiDAR device align with each other at a pre-determined synchronization point in view of their respective acquisition timestamps.
19. The system of claim 18 , wherein the synchronization point is determined based on a type of the target object.
20. The system of claim 16 , wherein the first bounding box is a 2-D bounding box generated based on a first piece of sensor data from the camera, and wherein the second bounding box is a 3-D bounding box generated based on a second piece of sensor data from the LiDAR device.
21. The system of claim 16 , wherein performing the analysis further comprises:
determining whether the first bounding box and the second bounding box match each other.