IP Library › Granted Patent US 12,298,431
Granted Patent B1
US 12,298,431 · App. 17/733,430 · Granted May 13, 2025

Radar data masks in autonomous vehicle simulations

Inventors: Anas Lasram (South San Francisco, CA); James Graham Dolan (Sarasota, FL); Ximing Li (San Mateo, CA)
Assignee: Zoox, Inc.
G01S7/40G01S7/406G01S7/412G06F30/20B60W60/001B60W2420/408
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 12,298,431
App. No.
17/733,430
Granted
May 13, 2025
Kind
B1
Abstract

A simulation system may generate radar data for synthetic simulations of autonomous vehicles by determining and applying radar masks for object radar data based on the attributes of simulated objects. A simulation system may determine a simulated object within a region of a simulated environment, and may apply a radar mask to determine the radar data within the region based on attributes of the simulated object. Such attributes may include the material properties, object type, and/or distance of the simulated object from the simulation sensors. Radar masks may be determining using masking percentages based on combinations of object attributes, and masks may be applied individually or by combining multiple masks for multiple occluding objects, in order to more accurately simulate the behavior of real-world radar signals in autonomous vehicle simulations.

Claims (91)

1. A system comprising:

one or more processors; and

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

receiving simulation data representing a first simulated object in a simulation;

determining, based at least in part on the simulation data, a first material property associated with the first simulated object;

determining, based at least in part on the first material property, a first radar mask associated with the first simulated object;

performing a first ray tracing operation to determine simulated radar data associated with the first simulated object, wherein performing the first ray tracing operation comprises:

determining a first ray from a location of a simulated radar sensor in the simulation to the first simulated object;

determining, based at least in part on the first radar mask, that the first ray is permitted to pass through the first simulated object; and

determining a first radar data point associated with the first ray tracing operation, wherein the first radar data point includes data based at least in part on a second simulated object occluded from the simulated radar sensor by the first simulated object; and

providing the simulated radar data associated with the first simulated object as input to the simulated radar sensor during the simulation.

2. The system of claim 1 , the operations further comprising:

performing a second ray tracing operation, wherein performing the second ray tracing operation comprises:

determining a second ray from the location of the simulated radar sensor in the simulation to the first simulated object;

determining, based at least in part on the first radar mask, that the second ray is permitted to pass through the first simulated object;

determining, based at least in part on a second radar mask associated with the second simulated object, that the second ray is permitted to pass through the second simulated object; and

determining a second radar data point associated with the second ray tracing operation, wherein the second radar data point includes data based at least in part on a third simulated object occluded from the simulated radar sensor by the first simulated object and the second simulated object; and

providing the second radar data point, as part of the simulated radar data associated with the first simulated object, as input to the simulated radar sensor during the simulation.

3. The system of claim 1 , wherein determining the first radar mask comprises:

determining an attribute associated with the first simulated object, wherein the attribute includes at least one of an object classification or a distance between the first simulated object and the simulated radar sensor; and

determining a percentage value associated with the first radar mask, based at least in part on the first material property and the attribute.

4. The system of claim 1 , wherein determining the first radar mask comprises:

determining a first portion of the first simulated object associated with the first material property;

determining a first percentage value associated with the first material property;

determining a second portion of the first simulated object associated with a second material property different from the first material property;

determining a second percentage value associated with the second material property; and

determining the first radar mask based at least in part on the first percentage value and the second percentage value.

5. The system of claim 4 , wherein determining the first radar mask further comprises:

determining a first region of the first radar mask corresponding to the first portion of the first simulated object;

determining a second region of the first radar mask corresponding to the second portion of the first simulated object; and

constructing, as the first radar mask, a mask configured to provide a first percentage of simulated radar data based on the first percentage value within the first region, and a second percentage of simulated radar data based on the second percentage value within the second region.

6. One or more non-transitory computer-readable media storing instructions executable by a processor, wherein the instructions, when executed, cause the processor to perform operations comprising:

receiving simulation data representing a first simulated object in a simulation;

determining, based at least in part on the simulation data, a first attribute associated with the first simulated object;

determining, based at least in part on the first attribute, a first radar mask associated with the first simulated object;

determining radar data associated with the first simulated object, based at least in part on the first radar mask, wherein determining the radar data comprises:

performing a first ray tracing operation;

determining, based at least in part on the first radar mask, that a first ray associated with the first ray tracing operation is permitted to pass through the first simulated object; and

determining a first radar data point associated with the first ray tracing operation, wherein the first radar data point includes data based at least in part on a second simulated object occluded from a simulated radar sensor by the first simulated object; and

providing the radar data associated with the first simulated object as input to the simulated radar sensor during the simulation.

7. A method comprising:

receiving simulation data representing a first simulated object in a simulation;

determining, based at least in part on the simulation data, a first attribute associated with the first simulated object;

determining, based at least in part on the first attribute, a first radar mask associated with the first simulated object, wherein determining the first radar mask comprises:

determining a first portion of the first simulated object associated with the first attribute, wherein the first attribute includes a first material property;

determining a first percentage value based at least in part on the first attribute;

determining a second portion of the first simulated object associated with a second attribute, wherein the second attribute includes a second material property different from the first material property;

determining a second percentage value based at least in part on the second attribute; and

determining the first radar mask based at least in part on the first percentage value and the second percentage value;

determining radar data associated with the first simulated object, based at least in part on the first radar mask; and

providing the radar data associated with the first simulated object as input to a simulated radar sensor during the simulation.

8. The method of claim 7 , wherein determining the radar data comprises:

performing a first ray tracing operation;

determining, based at least in part on the first radar mask, that a first ray associated with the first ray tracing operation is permitted to pass through the first simulated object; and

determining a first radar data point associated with the first ray tracing operation, wherein the first radar data point includes data based at least in part on a second simulated object occluded from the simulated radar sensor by the first simulated object.

9. The method of claim 8 , wherein determining the radar data further comprises:

performing a second ray tracing operation;

determining, based at least in part on the first radar mask, that a second ray associated with the second ray tracing operation is permitted to pass through the first simulated object;

determining, based at least in part on a second radar mask associated with the second simulated object, that the second ray is permitted to pass through the second simulated object; and

determining a second radar data point associated with the second ray tracing operation, wherein the second radar data point includes data based at least in part on a third simulated object occluded from the simulated radar sensor by the second simulated object.

10. The method of claim 7 , wherein determining the first radar mask further comprises:

determining a second attribute associated with the first simulated object, wherein the second attribute includes at least one of an object classification or a distance between the first simulated object and the simulated radar sensor; and

modifying the first percentage value based at least in part on the second attribute.

11. The method of claim 7 , wherein determining the first radar mask further comprises:

determining a first region of the first radar mask corresponding to the first portion of the first simulated object;

determining a second region of the first radar mask corresponding to the second portion of the first simulated object; and

constructing, as the first radar mask, a mask configured to provide a first percentage of simulated radar data based on the first percentage value within the first region, and a second percentage of simulated radar data based on the second percentage value within the second region.

12. The method of claim 7 , wherein determining the radar data associated with the first simulated object comprises:

determining, based at least in part on the simulation data, initial radar data associated with the first simulated object, wherein the initial radar data includes a plurality of radar data points; and

determining, as the radar data, modified radar data by applying the first radar mask to the initial radar data associated with the first simulated object, wherein the modified radar data includes a subset of the plurality of radar data points.

13. The one or more non-transitory computer-readable media of claim 6 , wherein determining the radar data further comprises:

performing a second ray tracing operation;

determining, based at least in part on the first radar mask, that a second ray associated with the second ray tracing operation is permitted to pass through the first simulated object;

determining, based at least in part on a second radar mask associated with the second simulated object, that the second ray is permitted to pass through the second simulated object; and

determining a second radar data point associated with the second ray tracing operation, wherein the second radar data point includes data based at least in part on a third simulated object occluded from the simulated radar sensor by the second simulated object.

14. The one or more non-transitory computer-readable media of claim 6 , wherein the first attribute includes a material property associated with the first simulated object, and wherein determining the first radar mask comprises:

determining a percentage value associated with the material property; and

determining the first radar mask based at least in part on the percentage value.

15. The one or more non-transitory computer-readable media of claim 14 , wherein determining the first radar mask further comprises:

determining a second attribute associated with the first simulated object, wherein the second attribute includes at least one of an object classification or a distance between the first simulated object and the simulated radar sensor; and

modifying the percentage value based at least in part on the second attribute.

16. The one or more non-transitory computer-readable media of claim 6 , wherein determining the first radar mask comprises:

determining a first portion of the first simulated object associated with the first attribute, wherein the first attribute includes a first material property;

determining a first percentage value based at least in part on the first attribute;

determining a second portion of the first simulated object associated with a second attribute, wherein the second attribute includes a second material property different from the first material property;

determining a second percentage value based at least in part on the second attribute; and

determining the first radar mask based at least in part on the first percentage value and the second percentage value.

17. The one or more non-transitory computer-readable media of claim 16 , wherein determining the first radar mask further comprises:

determining a first region of the first radar mask corresponding to the first portion of the first simulated object;

determining a second region of the first radar mask corresponding to the second portion of the first simulated object; and

constructing, as the first radar mask, a mask configured to provide a first percentage of simulated radar data based on the first percentage value within the first region, and a second percentage of simulated radar data based on the second percentage value within the second region.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 2, 2022
From: LASRAM, ANAS; DOLAN, JAMES GRAHAM; LI, XIMING
To: ZOOX, INC.
Reel/Frame 059780/0213 →
References Cited (10)
US 10929711B1 · Pfeiffer · 2021 [cited by examiner]
US 11276177B1 · Tsai · 2022 [cited by examiner]
US 20190171912A1 · Vallespi-Gonzalez · 2019 [cited by applicant]
US 20200103523A1 · Liu · 2020 [cited by examiner]
US 20200301799A1 · Manivasagam · 2020 [cited by examiner]
US 20210294346A1 · Mao · 2021 [cited by applicant]
US 20220284624A1 · Nimmagadda · 2022 [cited by examiner]
US 20230311930A1 · Lasram · 2023 [cited by applicant]
US 20230311932A1 · Lasram · 2023 [cited by applicant]
PCT Search Report and Written Opinion mailed Jul. 14, 2023 for PCT application No. PCT/US23/16755, 10 pages. [cited by applicant]