Method and system for operating an autonomous agent with incomplete environmental information

Patent metadata

Field	Value
Publication number	US-11745764-B2
Application number	US-202217941251-A
Country	US
Kind code	B2
Filing date	Sep 9, 2022
Priority date	Apr 2, 2021
Publication date	Sep 5, 2023
Grant date	Sep 5, 2023

Abstract

A system for operating an autonomous agent with incomplete environmental information can include and/or interface an autonomous operating system and an autonomous agent. A method for operating an autonomous agent with incomplete environmental information includes any or all of: receiving a set of inputs; determining a set of known objects in the ego vehicle's environment; determining a set of blind regions in the ego vehicle's environment; and inserting a set of virtual objects into the set of blind regions; selecting a set of virtual objects based on the set of blind regions; operating the autonomous agent based on the set of virtual objects; and/or any other suitable processes.

First claim

We claim:

1. A method comprising:
with vehicle sensor data, determining an environmental representation for an environment of an autonomous vehicle, wherein the environmental representation comprises a set of known objects;
identifying a set of unknown regions in the environmental representation;
determining an intersection of the set of unknown regions and a set of conflict zones labeled within a map;
based on the intersection, updating the environmental representation to include a set of virtual objects; and
operating the autonomous vehicle based on the updated environmental representation.

2. The method of claim 1 , wherein the set of labeled conflict zones is determined at least in part based on a behavior associated with the autonomous vehicle.

3. The method of claim 2 , further comprising: performing a simulation based on the set known objects and the set of virtual objects.

4. The method of claim 3 , further comprising: controlling the autonomous vehicle based on the simulation.

5. The method of claim 3 , wherein the behavior is a simulated behavior assigned to the autonomous vehicle in the simulation.

6. The method of claim 3 , wherein the simulation comprises a forward simulation performed in accordance with a predetermined cycle frequency.

7. The method of claim 1 , wherein updating the environmental representation based on the intersection comprises:
identifying a subset of unknown regions of the set of unknown regions which overlap the set of labeled conflict zones; and
including a virtual object of the set within each unknown region of the subset of unknown regions.

8. The method of claim 7 , wherein the set of virtual objects are selected from a predetermined set of virtual objects based on a size parameter of a respective unknown region of the subset of unknown regions.

9. The method of claim 1 , further comprising: assigning a first set of parameters to each of the set of virtual objects, wherein the first set of parameters is determined at least in part based on a second set of parameters associated with the set of known objects.

10. The method of claim 1 , further comprising assigning a set of parameters to each virtual object of the set, wherein the set of parameters comprises a speed.

11. The method of claim 10 , wherein the speed is determined based on information associated with the set of known objects.

12. The method of claim 11 , wherein the information comprises a set of historical speeds associated with the set of known objects.

13. The method of claim 1 , wherein the environmental representation characterizes the environment of the autonomous vehicle.

14. The method of claim 1 , wherein updating the environmental representation to include a set of virtual objects is further based on a probability associated with a respective unknown region.

15. The method of claim 14 , wherein the environmental representation is updated based on the probability exceeding a threshold.

16. The method of claim 14 , wherein the probability is determined based on historical sensor data associated with a location corresponding to the unknown region of the subset.

17. The method of claim 14 , wherein the probability is determined based on historical sensor data associated with a set of known objects in the characterized environment.

18. The method of claim 14 , wherein the probability is determined based on a change in a number of known objects in the environmental representation.

19. The method of claim 1 , wherein the set of unknown regions is identified based on a set of height metrics associated with the characterized environment.

20. The method of claim 19 , wherein each of the set of unknown regions has a height exceeding a predetermined height threshold relative to a ground level of the characterized environment.

Assignees

• May Mobility Inc

Inventors

• Patel Sajan
• Johnson Collin
• Meyer Gregory
• Olson Edwin B

Classifications

• B60W2554/4041

  Position · CPC title

• B60W2420/408

  Radar; Laser, e.g. lidar · CPC title

• B60W60/0011 Primary

  involving control alternatives for a single driving scenario, e.g. planning several paths to avoid obstacles · CPC title

• B60W40/04

  Traffic conditions · CPC title

• B60W60/0015

  specially adapted for safety · CPC title