Granted Patent B1

US 12,162,500 · App. 17/829,114 · Granted Dec 10, 2024

Inventors: Joshua Dean Egbert (Redwood City, CA); Joseph Funke (Redwood City, CA); Xianan Huang (Foster City, CA); Dhanushka Nirmevan Kularatne (Fremont, CA); David Evan Zlotnik (Menlo Park, CA)

Assignee: Zoox, Inc.

B60W50/0097B60W50/0205B60W60/0027B60W2520/06B60W2556/10

Abstract

Claims (65)

1. A system comprising:

one or more processors; and

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

receiving tracking error data associated with a vehicle in an environment, the tracking error data comprising a difference between a prior predicted vehicle state and a measured vehicle state associated with the prior predicted vehicle state;

receiving current vehicle state data indicating a current state of the vehicle in the environment;

inputting, into a model, the current vehicle state data and the tracking error data;

receiving, from the model, one or more of a lateral error associated with a future predicted vehicle state or a heading error associated with the future predicted vehicle state;

determining a distance along a current trajectory of the vehicle;

determining, based at least in part on the one or more of the lateral error, the heading error, or the distance, a buffer region around a representation of the vehicle associated with the future predicted vehicle state;

determining, based at least in part on the buffer region, an intersection between the vehicle at the future predicted vehicle state and an object in the environment; and

controlling the vehicle based at least in part on the intersection.

2. The system of claim 1 , wherein controlling the vehicle comprises:

determining, based at least in part on the intersection, a candidate trajectory for the vehicle to follow; and

controlling the vehicle based at least in part on the candidate trajectory.

3. The system of claim 1 , wherein predicting the intersection comprises determining an amount that the buffer region around the representation of the vehicle intersects with a representation of the object.

4. The system of claim 1 , wherein:

the current vehicle state data comprises steering rate data or steering angle data, and

determining the buffer region is further based at least in part on the steering rate data or the steering angle data.

5. The system of claim 1 , wherein determining the buffer region comprises:

determining, based at least in part on the tracking error data, a maximum observed tracking error; and

scaling the lateral error or the heading error based at least in part on the tracking error data and the distance along the current trajectory of the vehicle.

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

determining an error representing a difference between a predicted state of a vehicle and a current state of the vehicle associated with the predicted state, the error comprising one or more of a heading error or a position error;

determining a buffer region around a representation of the vehicle based at least in part on the error and historical error data; and

controlling the vehicle relative to an object in an environment based at least in part on the buffer region.

7. The one or more non-transitory computer-readable media of claim 6 , wherein determining the buffer region comprises:

inputting the one or more of the current state of the vehicle, the error, a distance along a trajectory of the vehicle, or historical error data into a model; and

receiving, from the model, the buffer region.

8. The one or more non-transitory computer-readable media of claim 6 , wherein determining the buffer region comprises:

determining, based at least in part on tracking error data, a maximum observed tracking error; and

scaling the position error or the heading error based at least in part on the tracking error data and a distance along a current trajectory of the vehicle.

9. The one or more non-transitory computer-readable media of claim 6 , wherein controlling the vehicle relative to the object comprises:

predicting, based at least in part on the buffer region, an intersection between the vehicle and the object; and

determining a candidate trajectory for the vehicle to follow based at least in part on the intersection.

10. The one or more non-transitory computer-readable media of claim 6 , the operations further comprising:

dynamically adjusting the buffer region around the representation of the vehicle based at least in part on tracking error data and a distance along a trajectory of the vehicle.

11. The one or more non-transitory computer-readable media of claim 6 , the operations further comprising:

determining that the buffer region around the representation of the vehicle and a representation of the object overlap;

determining, based at least in part on the overlap, a potential intersection between the vehicle and the object; and

updating an instruction to control the vehicle relative to the object in the environment further based at least in part on the overlap.

12. The one or more non-transitory computer-readable media of claim 6 , the operations further comprising:

receiving, by a model, steering rate data or steering angle data representing the predicted state of the vehicle, and

determining, by the model, the buffer region around the representation of the vehicle further based at least in part on the steering rate data or the steering angle data.

13. The one or more non-transitory computer-readable media of claim 6 , wherein the buffer region comprises different size or heading from a size or heading associated with the vehicle.

14. The one or more non-transitory computer-readable media of claim 6 , wherein the buffer region around the representation of the vehicle comprises a heading that is different from a predicted heading of the vehicle.

15. The one or more non-transitory computer-readable media of claim 6 , wherein the error comprises a first error and the operations further comprising:

determining a second error associated with a previous predicted state of the vehicle;

determining a maximum error based at least in part on the first error and the second error; and

determining the buffer region around the representation of the vehicle further based at least in part on the maximum error.

16. The one or more non-transitory computer-readable media of claim 6 , wherein the buffer region is a first buffer region, and the operations further comprising:

determining an object type associated with the object in the environment; and

determining, based at least in part on the object type, a second buffer region around the representation of the vehicle,

wherein controlling the vehicle relative to the object in the environment is further based at least in part on the second buffer region.

17. A method comprising:

determining an error representing a difference between a predicted state of a vehicle and a current state of the vehicle associated with the predicted state, the error comprising one or more of a heading error or a position error;

determining a buffer region around a representation of the vehicle based at least in part on the error and historical error data; and

controlling the vehicle relative to an object in an environment based at least in part on the buffer region.

18. The method of claim 17 , wherein determining the buffer region comprises:

inputting the one or more of the current state of the vehicle, the error, a distance along a current trajectory of the vehicle, or historical error data into a model; and

receiving, from the model, the buffer region.

19. The method of claim 17 , wherein determining the buffer region comprises:

determining, based at least in part on tracking error data, a maximum observed tracking error; and

scaling the position error or the heading error based at least in part on the tracking error data and a distance along a current trajectory of the vehicle.

20. The method of claim 17 , further comprising:

dynamically adjusting the buffer region around the representation of the vehicle based at least in part on tracking error data and a distance along a trajectory of the vehicle.

Assignments (1)

Cited By (10)

US 12,479,471 US 12,491,907 US 12,515,648 US 12,536,473 US 12,541,718 US 12,570,255 US 12,589,739 US 12,608,655 US 12,731,080 US 12,737,687