Granted Patent B2

US 12,649,492 · App. 18/240,860 · Granted Jun 9, 2026

Inventors: Derek Lau (San Francisco, CA); Christopher Ostafew (Mountain View, CA)

Assignee: Nissan North America, Inc.

B60W60/0027B60W30/0956B60W40/105B60W2554/80

Abstract

Claims (69)

1 . A method for determining a speed plan for an autonomous vehicle (AV), comprising:

placing, for future time steps, planned locations of the AV in an occupancy grid, wherein the planned locations are based on a strategic speed plan that is determined without taking world objects into account;

placing, for at least some of the future time steps, predicted locations of the world objects in the occupancy grid;

adding respective buffer distances corresponding to the predicted locations in the occupancy grid;

adding virtual predictions to the occupancy grid, wherein the virtual predictions include a predicted path of virtual lead vehicles or virtual world objects;

obtaining an estimated speed plan for the AV based on the occupancy grid;

obtaining the speed plan from the estimated speed plan;

controlling the AV according to the speed plan;

generating a tactical speed plan based upon an intersection with the virtual lead vehicles or the virtual world objects; and

modifying the speed plan for a discrete time step based on the tactical speed plan until the virtual lead vehicles or the virtual world objects are removed from the occupancy grid.

2 . The method of claim 1 , further comprising:

identifying a world object of the world objects as an along path world object, wherein the respective buffer distances corresponding to the world object are based on a time headway to the world object.

3 . The method of claim 1 , further comprising:

identifying a world object of the world objects as a crossing world object, wherein the respective buffer distances corresponding to the world object are based on a time to collision between the AV and the world object.

4 . The method of claim 1 , wherein the speed plan is obtained by solving an optimization problem that minimizes a change in velocity of the AV, minimizes an acceleration change of the AV, and minimizes differences from the strategic speed plan.

5 . The method of claim 4 , wherein the optimization problem uses kinematic constraints of the AV, and distance constraints related to distances between the AV and an along path vehicle.

6 . The method of claim 1 , further comprising:

in response to determining that a crossing lane is obstructed to sensors of the AV, placing a virtual along path vehicle in the occupancy grid.

7 . The method of claim 1 , wherein controlling the AV according to the speed plan comprises:

in response to determining that the speed plan causes the AV to stop in an intersection:

causing the AV to stop at a virtual stop line that is added to the occupancy grid;

continually updating the occupancy grid and identifying an updated speed plan until the updated speed plan is such that the AV does not stop in the intersection; and

controlling the AV according to the updated speed plan.

8 . An autonomous vehicle (AV), comprising:

a memory; and

a processor, the processor configured to execute instructions stored in the memory to determine a speed plan for the AV, the instructions comprise:

placing, for future time steps, planned locations of the AV in an occupancy grid, wherein the planned locations are based on a strategic speed plan that is determined without taking world objects into account;

placing, for at least some of the future time steps, predicted locations of the world objects in the occupancy grid;

adding respective buffer distances corresponding to the predicted locations in the occupancy grid;

adding virtual predictions to the occupancy grid, wherein the virtual predictions include a predicted path of virtual lead vehicles or virtual world objects;

obtaining an estimated speed plan for the AV based on the occupancy grid;

obtaining the speed plan from the estimated speed plan;

controlling the AV according to the speed plan;

generating a tactical speed plan, with an optimized speed plan tool (OSP), based upon an intersection with the virtual lead vehicles or the virtual world objects; and

modifying the speed plan for a discrete time based on the tactical speed plan until the virtual lead vehicles or the virtual world objects are removed from the occupancy grid.

9 . The AV of claim 8 , wherein the processor is further configured to execute instruction to:

identify a world object of the world objects as an along path world object, wherein the respective buffer distances corresponding to the world object are based on a time headway to the world object.

10 . The AV of claim 8 , wherein the processor is further configured to execute instruction to:

identify a world object of the world objects as a crossing world object, wherein the respective buffer distances corresponding to the world object are based on a time to collision between the AV and the world object.

11 . The AV of claim 8 , wherein the speed plan is obtained by solving an optimization problem that minimizes a change in velocity of the AV, minimizes an acceleration change of the AV, and minimizes differences from the strategic speed plan.

12 . The AV of claim 11 , wherein the optimization problem uses kinematic constraints of the AV, and distance constraints related to distances between the AV and an along path vehicle.

13 . The AV of claim 8 , wherein the processor is further configured to execute instruction to:

in response to determining that a crossing lane is obstructed to sensors of the AV, place a virtual along path vehicle in the occupancy grid.

14 . The AV of claim 8 , wherein to control the AV according to the speed plan comprises to:

in response to determining that the speed plan causes the AV to stop in an intersection:

cause the AV to stop at a virtual stop line that is added to the occupancy grid;

continually update the occupancy grid and identifying an updated speed plan until the updated speed plan is such that the AV does not stop in the intersection; and

control the AV according to the updated speed plan.

15 . A non-transitory computer-readable medium storing instructions operable to cause one or more processors to perform operations for determining a speed plan for an autonomous vehicle (AV), the operations comprising:

placing, for future time steps, planned locations of the AV in an occupancy grid, wherein the planned locations are based on a strategic speed plan that is determined without taking world objects into account;

placing, for at least some of the future time steps, predicted locations of the world objects in the occupancy grid;

adding respective buffer distances corresponding to the predicted locations in the occupancy grid;

adding virtual predictions to the occupancy grid, wherein the virtual predictions include a predicted path of virtual lead vehicles or virtual world objects;

obtaining an estimated speed plan for the AV based on the occupancy grid;

obtaining the speed plan from the estimated speed plan;

controlling the AV according to the speed plan;

generating a tactical speed plan based upon an intersection with the virtual lead vehicles or the virtual world objects; and

modifying the speed plan for a discrete time based on the tactical speed plan until the virtual lead vehicles or the virtual world objects are removed from the occupancy grid.

16 . The non-transitory computer-readable medium of claim 15 , wherein the operations further comprise:

identifying a world object of the world objects as an along path world object, wherein the respective buffer distances corresponding to the world object are based on a time headway to the world object.

17 . The non-transitory computer-readable medium of claim 15 , wherein the operations further comprise:

identifying a world object of the world objects as a crossing world object, wherein the respective buffer distances corresponding to the world object are based on a time to collision between the AV and the world object.

18 . The non-transitory computer-readable medium of claim 15 , wherein the speed plan is identified by solving an optimization problem that minimizes a change in velocity of the AV, minimizes an acceleration change of the AV, and minimizes differences from the strategic speed plan, and wherein the optimization problem uses kinematic constraints of the AV, and distance constraints related to distances between the AV and an along path vehicle.

19 . The non-transitory computer-readable medium of claim 15 , wherein the operations further comprise:

in response to determining that a crossing lane is obstructed to sensors of the AV, placing a virtual along path vehicle in the occupancy grid.

20 . The non-transitory computer-readable medium of claim 15 , wherein controlling the AV according to the speed plan comprises:

in response to determining that the speed plan causes the AV to stop in an intersection:

causing the AV to stop at a virtual stop line that is added to the occupancy grid;

continually updating the occupancy grid and identifying an updated speed plan until the updated speed plan is such that the AV does not stop in the intersection; and controlling the AV according to the updated speed plan.

Assignments (1)

Continuity (1)

References Cited (29)