Granted Patent B2

US 12,479,424 · App. 18/388,525 · Granted Nov 25, 2025

Inventors: Jefferson Bradfield Packer (San Francisco, CA); William Anthony Silva (San Francisco, CA); Zhenqi Huang (San Carlos, CA)

Assignee: Zoox, Inc.

B60W30/09B60W30/0953B60W30/0956G05D1/0088G08G1/166

Abstract

Claims (77)

1 . A method comprising:

one or more of receiving or determining a probability density function associated with one or more of a vehicle in an environment or an object in the environment;

determining a region of the environment that is predicted to be occupied by both the vehicle and the object;

determining a likelihood of collision between the vehicle and the object based at least in part on an overlap between the probability density function and the region; and

controlling the vehicle based at least in part on the likelihood of collision.

2 . The method of claim 1 , further comprising:

determining that the likelihood of collision is above a threshold value; and

further wherein controlling the vehicle comprises modifying a vehicle trajectory based at least in part on the likelihood of collision being above the threshold value.

3 . The method of claim 1 , further comprising:

receiving one or more of a vehicle trajectory associated with the vehicle traversing the environment or a path polygon associated with the vehicle traversing the environment; and

receiving an object trajectory associated with the object traversing the environment,

wherein the region comprises a portion of the path polygon associated with the vehicle traversing the environment.

4 . The method of claim 3 , further comprising:

determining a modified vehicle trajectory;

determining a second likelihood of collision between the vehicle and the object based at least in part on the modified vehicle trajectory and the object trajectory; and

determining that the second likelihood of collision is less than a threshold value.

5 . The method of claim 1 , wherein the region is based at least in part on a first parameter of the vehicle and a second parameter of the object, and the likelihood of collision is based at least in part on a size of the region.

6 . The method of claim 1 , wherein:

the probability density function is a first probability density function associated with the vehicle,

the method further comprises receiving a second probability density function associated with the object,

determining the overlap is further based at least in part on the second probability density function, and

the overlap is further associated with position cones associated with the vehicle and the object.

7 . The method of claim 1 , wherein controlling the vehicle based at least in part on the likelihood of collision comprises at least one of:

maintaining a first trajectory associated with the vehicle;

modifying a speed associated with the first trajectory; or

modifying a direction of travel associated with the first trajectory.

8 . The method of claim 1 , wherein the region is defined at least in part by a range of times during which the vehicle and the object are predicted to be contemporaneously located in the region, and further comprising:

determining an object entry time into the region;

determining an object exit time from the region;

determining a vehicle entry time into the region; and

determining a vehicle exit time from the region.

9 . A system comprising:

one or more processors; and

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

one or more of receiving or determining a probability density function associated with one or more of a vehicle in an environment and an object in the environment;

determining a region of the environment that is predicted to be occupied by both the vehicle and the object;

determining a likelihood of collision between the vehicle and the object based at least in part on an overlap between the probability density function and the region; and

controlling the vehicle based at least in part on the likelihood of collision.

10 . The system of claim 9 , the operations further comprising:

determining that the likelihood of collision is above a threshold value; and

further wherein controlling the vehicle comprises modifying a vehicle trajectory based at least in part on the likelihood of collision being above the threshold value.

11 . The system of claim 9 , the operations further comprising:

receiving an object trajectory associated with the object traversing the environment;

determining, as a modified vehicle trajectory and based at least in part on the likelihood of collision, a modification to a current vehicle trajectory;

determining a second likelihood of collision between the vehicle and the object based at least in part on the modified vehicle trajectory and the object trajectory; and

determining that the second likelihood of collision is less than a threshold value.

12 . The system of claim 9 , wherein the region is based at least in part on a first parameter of the vehicle and a second parameter of the object, and

the likelihood of collision is based at least in part on a size of the region.

13 . The system of claim 9 , wherein controlling the vehicle based at least in part on the likelihood of collision comprises at least one of:

maintaining a first trajectory associated with the vehicle;

modifying a speed associated with the first trajectory; or

modifying a direction of travel associated with the first trajectory.

14 . The system of claim 9 , wherein the region is defined at least in part by a range of times during which the vehicle and the object are predicted to be contemporaneously located in the region, and further comprising:

determining an object entry time into the region;

determining an object exit time from the region;

determining a vehicle entry time into the region; and

determining a vehicle exit time from the region.

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

one or more of receiving or determining a probability density function associated with one or more of a vehicle in an environment or an object in the environment;

determining a region of the environment that is predicted to be contemporaneously occupied, during a range of times, by both the vehicle and the object;

determining a likelihood of collision between the vehicle and the object based at least in part on an overlap between the probability density function and the region; and

controlling the vehicle based at least in part on the likelihood of collision.

16 . The one or more non-transitory computer-readable media of claim 15 , the operations further comprising:

determining that the likelihood of collision is above a threshold value; and

further wherein controlling the vehicle comprises modifying a vehicle trajectory based at least in part on the likelihood of collision being above the threshold value.

17 . The one or more non-transitory computer-readable media of claim 15 , the operations further comprising:

receiving an object trajectory associated with the object traversing the environment;

determining, as a modified vehicle trajectory, a modification to a vehicle trajectory;

determining a second likelihood of collision between the vehicle and the object based at least in part on the modified vehicle trajectory and the object trajectory; and

determining that the second likelihood of collision is less than a threshold value.

18 . The one or more non-transitory computer-readable media of claim 15 , wherein the region is based at least in part on a first parameter of the vehicle and a second parameter of the object, and the likelihood of collision is based at least in part on a size of the region.

19 . The one or more non-transitory computer-readable media of claim 15 , wherein the overlap is further associated with position cones associated with the vehicle and the object.

20 . The one or more non-transitory computer-readable media of claim 15 , wherein the region is defined at least in part by a range of times during which the vehicle and the object are predicted to be contemporaneously located in the region, and further comprising:

determining an object entry time into the region;

determining an object exit time from the region;

determining a vehicle entry time into the region; and

determining a vehicle exit time from the region.

Assignments (1)

Continuity (3)

References Cited (44)