Granted Patent B2

US 12,319,313 · App. 18/387,367 · Granted Jun 3, 2025

Inventors: Sajan Patel (Ann Arbor, MI); Collin Johnson (Ann Arbor, MI); Gregory Meyer (Ann Arbor, MI); Edwin B. Olson (Ann Arbor, MI)

Assignee: May Mobility, Inc.

B60W60/0011B60W40/04B60W60/0015G01S17/89G01S17/931B60W2420/408B60W2554/404B60W2556/10

Abstract

Claims (50)

1. A method for controlling a vehicle, the method comprising:

collecting sensor data from a set of sensors of the vehicle;

based on the sensor data, detecting:

a set of known objects;

a set of obstructed regions;

for a time interval in the future, simulating the vehicle's movement through an environment, wherein the environment comprises:

a 1 st set of objects corresponding to the set of known objects;

a 2 nd set of objects based on the set of obstructed regions, the 2 nd set of objects comprising a set of phantom objects, wherein the 2 nd set of objects is determined at least in part based on historical sensor data collected at the set of sensors;

based on the simulated movement, selecting an action for the vehicle; and

controlling the vehicle according to the action.

2. The method of claim 1 , wherein controlling the vehicle comprises autonomously operating the vehicle according to the action.

3. The method of claim 1 , further comprising collecting a second set of sensor data after controlling the vehicle according to the action and determining, based on the second set of sensor data that at least a portion of the phantom objects are determined to not exist.

4. The method of claim 3 , further determining, based on the second set of sensor data that a second portion of the phantom objects are determined to exist.

5. The method of claim 1 , wherein the 2 nd set of objects is associated with a set of phantom object types, wherein the set of phantom object types comprises multiple types.

6. The method of claim 5 , wherein the set of phantom object types is determined at least in part based on a set of locations associated with the set of obstructed regions.

7. The method of claim 6 , wherein the set of phantom object types is further determined based on a set of sizes associated with the set of obstructed regions.

8. The method of claim 1 , further comprising assigning a set of speeds to the 2 nd set of objects, wherein the vehicle's movement is simulated at least in part based on the set of speeds.

9. The method of claim 1 , further comprising refraining from assigning a phantom object of the set to a first obstructed region of the set of obstructed regions based on the historical sensor data.

10. A system for controlling a vehicle, the system comprising:

a computing subsystem at least partially operable as a simulator, the computing subsystem configured to:

collect sensor data from a set of sensors of the vehicle;

based on the sensor data, detect:

a set of known objects;

a set of obstructed regions;

for a time interval in the future, simulate the vehicle's movement through an environment, wherein the environment comprises:

a 1 st set of objects corresponding to the set of known objects;

a 2 nd set of objects based on the set of obstructed regions, the 2 nd set of objects comprising a set of phantom objects, wherein the 2 nd set of objects is determined at least in part based on historical sensor data collected at the set of sensors;

based on the simulated movement, select an action for the vehicle; and

control the vehicle according to the action.

11. The system of claim 10 , wherein controlling the vehicle comprises autonomously operating the vehicle according to the action.

12. The system of claim 10 , wherein at least a portion of the phantom objects are determined to not correspond to additional known objects after selecting the action for the vehicle.

13. The system of Claim of claim 12 , wherein a second portion of the phantom objects are determined to correspond to additional known objects after selecting the action for the vehicle.

14. The system of claim 10 , wherein the 2 nd set of objects is associated with a set of phantom object types, wherein the set of phantom object types comprises multiple types.

15. The system of claim 14 , wherein the set of phantom object types is determined at least in part based on a set of locations associated with the set of obstructed regions.

16. The system of claim 15 , wherein the set of phantom object types is further determined based on a set of sizes associated with the set of obstructed regions.

17. The system of claim 10 , further comprising assigning a set of speeds to the 2 nd set of objects.

18. The system of claim 17 , wherein the set of speeds comprises multiple speed values, wherein the vehicle's movement is simulated at least in part based on the set of speeds.

19. The system of claim 10 , wherein the computing subsystem is further configured to receive a second set of sensor data collected after controlling the vehicle according to the action and determine, based on the second set of sensor data that at least a portion of the phantom objects are determined to not exist.

20. A method for controlling a vehicle, the method comprising:

collecting sensor data from a set of sensors of the vehicle;

based on the sensor data, detecting:

a set of known objects;

a set of obstructed regions;

for a time interval in the future, simulating the vehicle's movement through an environment, wherein the environment comprises:

a 1 st set of objects corresponding to the set of known objects;

a 2 nd set of objects based on the set of obstructed regions, the 2 nd set of objects comprising a set of phantom objects;

based on the simulated movement, selecting an action for the vehicle;

controlling the vehicle according to the action;

collecting a second set of sensor data after controlling the vehicle according to the action; and

determining, based on the second set of sensor data that at least a portion of the phantom objects are determined to not exist.

Assignments (2)

Continuity (5)

References Cited (264)