IP Library › Granted Patent US 11,808,582
Granted Patent B1
US 11,808,582 · App. 17/305,090 · Granted Nov 7, 2023

System processing scenario objects during simulation

Inventor: James Graham Dolan (Foster City, CA)
Assignee: Zoox, Inc.
G01C21/32G01C21/3638
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,808,582
App. No.
17/305,090
Granted
Nov 7, 2023
Kind
B1
Abstract

Techniques associated with improving performance and realism of simulation instances associated with simulation testing of autonomous vehicles. In some cases, a simulation system may be configured to run a pre-simulation test to identify and store occlusion data to improve the performance of subsequent simulations associated with a shared scene or route.

Claims (56)

1. A system comprising:

one or more processors; and

one or more non-transitory computer-readable media storing instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:

receiving log data associated with a vehicle, the log data representing an environment traversed by the vehicle;

determining, based on the log data, one or more static objects in the environment;

determining, based on the log data, one or more dynamic objects in the environment;

executing a pre-simulation scenario, the pre-simulation scenario including a vehicle and the one or more static objects and excluding the one or more dynamic objects;

determining, based on the vehicle in the pre-simulation scenario and the one or more static objects in the pre-simulation scenario, an occluded area in the pre-simulation scenario;

storing, as results data, the occluded area associated with the pre-simulation scenario; and

outputting the results data for use by additional simulations including the occluded area.

2. The system as recited in claim 1 , wherein the pre-simulation scenario is executed in a three-dimensional environment and comprises simulating operations of the vehicle within the environment to be simulated.

3. The system as recited in claim 1 , wherein the operations further comprising generating the pre-simulation scenario without the dynamic objects.

4. The system as recited in claim 1 , operations further comprising filling the occluded area with synthetic scene data.

5. A method comprising:

determining an environment to be simulated in a vehicle simulation;

determining one or more static objects in the environment;

executing a pre-simulation scenario including the one or more static objects, the pre-simulation scenario including a vehicle;

determining an area occluded from the vehicle in the pre-simulation scenario based on the one or more static objects;

storing occluded area data indicating the area occluded from the vehicle; and

providing the occluded area data to a simulated scenario.

6. The method as recited in claim 5 , further comprising:

receiving data representing the environment to be simulated; and

generating a plurality of simulation scenarios based at least in part on the data.

7. The method as recited in claim 5 , further comprising:

receiving map data associated with the environment to be simulated; and

generating a plurality of simulation scenarios based at least in part on the map data, individual ones of the plurality of simulation scenarios including differing dynamic objects.

8. The method as recited in claim 5 , wherein the pre-simulation scenario is executed without a presence of dynamic objects.

9. The method as recited in claim 5 , wherein the simulated scenario comprises dynamic objects and wherein the pre-simulation scenario comprises simulating operations of the vehicle within the environment to be simulated.

10. The method as recited in claim 5 , further comprising filling the area occluded from the vehicle with synthetic data.

11. The method as recited in claim 10 , wherein filling the area occluded from the vehicle with synthetic data is based at least in part on real physical object data, procedurally generated object data, random object data, and/or generalized object data.

12. The method as recited in claim 5 , wherein storing occluded area data further comprises generating a grid and wherein the occluded area data is stored with respect to a corresponding position of the grid.

13. The method as recited in claim 5 , wherein the simulated scenario is a first simulated scenario of a plurality of simulated scenarios, the plurality of simulated scenarios including a second simulated scenario and the method further comprises:

executing a first simulation based at least in part on the first simulated scenario and the occluded area data; and

executing a second simulation based at least in part on the second simulated scenario and the occluded area data.

14. One or more non-transitory computer-readable media storing instructions that, when executed, cause one or more processors to perform operations comprising:

determining an environment to be simulated in a vehicle simulation;

determining one or more static objects in the environment;

executing a pre-simulation scenario including the one or more static objects, the pre-simulation scenario including a vehicle;

determining an area occluded from the vehicle in the pre-simulation scenario based on the one or more static objects;

storing occluded area data indicating the area occluded from the vehicle; and

providing the occluded area data to a simulated scenario.

15. The one or more non-transitory computer-readable media as recited in claim 14 , wherein that occluded area data is occlusion data and the pre-simulation scenario is executed without a presence of dynamic objects.

16. The one or more non-transitory computer-readable media as recited in claim 15 , wherein storing occluded area data further comprises generating a grid and wherein the occluded area data is stored with respect to a corresponding position of the grid.

17. The one or more non-transitory computer-readable media as recited in claim 14 , wherein the occluded area data comprises data associated with a first object, the data associated with the first object comprising at least one of:

a height of the first object;

a percentage of occlusion caused by the first object;

a class of the first object;

a boundary associated with the first object; and

one or more features of the first object.

18. The one or more non-transitory computer-readable media as recited in claim 14 , wherein the operations further comprise:

receiving log data associated with a physical vehicle, the log data representing an environment traversed by the physical vehicle; and

generating a plurality of simulation scenarios based at least in part on the log data.

19. The one or more non-transitory computer-readable media as recited in claim 14 , wherein the operations further comprise:

receiving map data associated with the environment to be simulated; and

wherein generating a plurality of simulation scenarios based at least in part on the map data.

20. The one or more non-transitory computer-readable media as recited in claim 14 , wherein the operations further comprise filling the area occluded from the vehicle with synthetic data.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 30, 2021
From: DOLAN, JAMES GRAHAM
To: ZOOX, INC.
Reel/Frame 056722/0921 →
Cited By (2)
US 12,503,140 US 12,724,689