Granted Patent B2

US 10,518,770 · App. 15/458,740 · Granted Dec 31, 2019

Inventors: Benjamin Kroop (Pittsburgh, PA); Matthew Way (Pittsburgh, PA); David McAllister Bradley (Pittsburgh, PA)

Assignee: UATC, LLC

B60W30/10B60W10/06B60W10/184B60W10/20B60W2420/42B60W2420/52

Abstract

Claims (44)

1. An autonomous vehicle (AV) comprising:

a sensor suite generating a live sensor view of a surrounding environment of the AV;

acceleration, braking, and steering systems; and

a control system executing an instruction set, causing the control system to:

implement a primary motion planner to continuously determine a first motion plan for the AV;

implement a secondary motion planner to continuously determine a backup motion plan for the AV, wherein continuously determining a backup plan comprises:

identifying an upcoming route trajectory associated with the first motion plan; and

dynamically adjusting one or more cost metrics associated with following the upcoming route trajectory associated with the first motion plan to cause the backup motion plan to diverge from the first motion plan, wherein the one or more cost metrics comprise a threshold below which the secondary motion planner will determine the backup motion plan to be different from the first motion plan, and above which the backup motion plan and the first motion plan will be the same; and

analyze the live sensor view to operate the acceleration, braking, and steering systems along sequential route trajectories selected between the first motion plan and the backup motion plan by selecting the backup motion plan, the backup motion plan preventing the primary motion planner from triggering a first teleassistance state for the first motion plan, the first teleassistance state corresponding to the primary motion planner requesting human assistance to continue in accordance with the first motion plan.

2. The AV of claim 1 , wherein the executed instruction set further causes the control system to:

determine a second teleassistance state in which the secondary motion planner requires remote human assistance to continue; and

transmit a teleassistance data package to a remote teleassistance system to enable human selection between the first motion plan and the backup motion plan.

3. The AV of claim 2 , wherein the teleassistance data package provides sensor data from the live sensor view utilized to generate a virtual simulation of each of the first motion plan and the backup motion plan for a human teleassistance operator to make a selection between the first motion plan and the backup motion plan.

4. The AV of claim 3 , wherein the executed instruction set further causes the control system to:

receive a teleassistance command corresponding to the selection by the human teleassistance operator; and

execute the teleassistance command to resolve the second teleassistance state.

5. The AV of claim 1 , wherein the primary motion planner and the secondary motion planner are included in a hierarchical set of motion planners simultaneously implemented by the control system.

6. A non-transitory computer readable medium storing instructions that, when executed by one or more processors of an autonomous vehicle (AV), cause the one or more processors to:

implement a primary motion planner to continuously determine a first motion plan for the AV;

implement a secondary motion planner to continuously determine a backup motion plan for the AV, wherein continuously determining a backup plan comprises:

identifying an upcoming route trajectory associated with the first motion plan; and

dynamically adjusting one or more cost metrics associated with following the upcoming route trajectory associated with the first motion plan to cause the backup motion plan from the first motion plan, wherein the one or more cost metrics comprise a threshold below which the secondary motion planner will determine the backup motion plan to be different from the first motion plan, and above which the backup motion plan and the first motion plan will be the same; and

analyze a live sensor view generated by a sensor suite of the AV to operate acceleration, braking, and steering systems of the AV along sequential route trajectories selected between the first motion plan and the backup motion plan by selecting the backup motion plan, the backup motion plan preventing the primary motion planner from triggering a first teleassistance state for the first motion plan, the first teleassistance state corresponding to the primary motion planner requesting human assistance to continue in accordance with the first motion plan.

7. The non-transitory computer readable medium of claim 6 , wherein the executed instructions further cause the one or more processors to:

determine a second teleassistance state in which the secondary motion planner requires remote human assistance to continue; and

transmit a teleassistance data package to a remote teleassistance system to enable human selection between the first motion plan and the backup motion plan.

8. The non-transitory computer readable medium of claim 7 , wherein the teleassistance data package provides sensor data from the live sensor view utilized to generate a virtual simulation of each of the first motion plan and the backup motion plan for a human teleassistance operator to make a selection between the first motion plan and the backup motion plan.

9. The non-transitory computer readable medium of claim 8 , wherein the executed instructions further cause the one or more processors to:

receive a teleassistance command corresponding to the selection by the human teleassistance operator; and

execute the teleassistance command to resolve the second teleassistance state.

10. The non-transitory computer readable medium of claim 6 , wherein the primary motion planner and the secondary motion planner are included in a hierarchical set of motion planners simultaneously implemented by the AV.

11. A computer-implemented method of operating an autonomous vehicle (AV), the method being performed by one or more processors and comprising:

implementing a primary motion planner to continuously determine a first motion plan for the AV;

implementing a secondary motion planner to continuously determine a backup motion plan for the AV, wherein continuously determining a backup motion plan comprises:

identifying an upcoming route trajectory associated with the first motion plan; and

dynamically adjusting one or more cost metrics associated with following the upcoming route trajectory associated with the first motion plan to cause the backup motion plan to diverge from the first motion plan, wherein the one or more cost metrics comprise a threshold below which the secondary motion planner will determine the backup motion plan to be different from the first motion plan, and above which the backup motion plan and the first motion plan will be the same; and

analyzing a live sensor view generated by a sensor suite of the AV to operate acceleration, braking, and steering systems of the AV along sequential route trajectories selected between the first motion plan and the backup motion plan by selecting the backup motion plan, the backup motion plan preventing the primary motion planner from triggering a first teleassistance state for the first motion plan, the first teleassistance state corresponding to the primary motion planner requesting human assistance to continue in accordance with the first motion plan.

12. The method of claim 11 , further comprising:

determining a second teleassistance state in which the secondary motion planner requires remote human assistance to continue; and

transmitting a teleassistance data package to a remote teleassistance system to enable human selection between the first motion plan and the backup motion plan.

13. The method of claim 12 , wherein the teleassistance data package provides sensor data from the live sensor view utilized to generate a virtual simulation of each of the first motion plan and the backup motion plan for a human teleassistance operator to make a selection between the first motion plan and the backup motion plan.

14. The method of claim 13 , further comprising:

receiving a teleassistance command corresponding to the selection by the human teleassistance operator; and

executing the teleassistance command to resolve the second teleassistance state.

Assignments (4)

Cited By (10)

US 12,240,494 US 12,296,849 US 12,319,313 US 12,371,067 US 12,384,410 US 12,394,311 US 12,441,364 US 12,559,132 US 12,559,143 US 12,594,961