Methods, devices, and systems for analyzing motion plans of autonomous vehicles

1. A computer-implemented method for analyzing a motion plan of an autonomous vehicle, the method comprising:

receiving data indicating a motion plan comprising at least one trajectory of an autonomous vehicle through an environment, wherein the at least one trajectory comprises a plurality of different points, wherein the motion plan is generated, determined, or selected based at least in part on a plurality of different constraints associated with the environment;

determining for at least one point of the plurality of different points, a sub measure of an influence of at least one of the plurality of different constraints on the motion plan at the at least one point, wherein a measure of the influence of the at least one constraint is indicative of a respective contribution of the at least one constraint to a generation, a determination, or a selection of the motion plan;

refining one or more instructions associated with the generation, the determination, or the selection of the motion plan based on the measure of the influence of the at least one constraint; and

instructing the autonomous vehicle to move in accordance with one or more motion plans that are generated, determined, or selected based on the one or more refined instructions.

2. The computer-implemented method of claim 1 , wherein determining the sub measure of the influence of the at least one constraint at the at least one point comprises determining a respective measure of a respective influence of the at least one constraint relative to one or more other constraints of the plurality of different constraints.

3. The computer-implemented method of claim 1 , wherein:

the environment comprises a plurality of different objects;

one or more of the plurality of different constraints are associated with the plurality of different objects; and

determining the sub measure of the influence of the at least one constraint at the at least one point comprises determining a contribution of at least one object of the plurality of different objects to the generation, the determination, or the selection of the motion plan.

4. The computer-implemented method of claim 1 , wherein:

the environment comprises a plurality of different objects;

one or more of the plurality of different constraints are associated with a plurality of different actions the autonomous vehicle is instructed to take with respect to the plurality of different objects; and

determining the sub measure of the influence of the at least one constraint at the at least one point comprises determining a contribution of at least one action of the plurality of different actions to the generation, the determination, or the selection of the motion plan.

5. The computer-implemented method of claim 4 , wherein the plurality of different actions instruct the autonomous vehicle to one or more of pass an object of the plurality of different objects, ignore an object of the plurality of different objects, queue behind an object of the plurality of different objects, maintain a position relative to an object of the plurality of different objects, maintain a distance between the autonomous vehicle and an object of the plurality of different objects, avoid an object of the plurality of different objects, or yield to an object of the plurality of different objects.

6. The computer-implemented method of claim 1 , wherein:

the motion plan is one or more of generated, determined, or selected based at least in part on its cost;

the plurality of different constraints are associated with a plurality of different functions for determining constituent costs of the motion plan; and

determining the sub measure of the influence of the at least one constraint at the at least one point comprises determining a contribution of at least one function of the plurality of different functions to the generation, the determination, or the selection of the motion plan.

7. The computer-implemented method of claim 1 , wherein determining the sub measure of the influence of the at least one constraint comprises determining, based at least in part on data utilized in one or more of the generating, the determining, or the selecting of the motion plan, the sub measure of the influence of the constraint.

8. The computer-implemented method of claim 7 , wherein determining the sub measure of the influence of the at least one constraint comprises replicating at least a portion of the data utilized in one or more of the generating, the determining, or the selecting of the motion plan.

9. The computer-implemented method of claim 8 , wherein determining the sub measure of the influence of the at least one constraint comprises deterministically recovering, based at least in part on a replication of at least the portion of the data utilized in one or more of the generating, the determining, or the selecting of the motion plan, a contribution of the constraint to the generation, the determination, or the selection of the motion plan.

10. The computer-implemented method of claim 1 , comprising generating, for display by a computing device, a user interface, wherein the user interface indicates, for each respective constraint of the plurality of different constraints, the respective measure of the respective influence of the respective constraint on the motion plan.

11. The computer-implemented method of claim 10 , wherein generating the user interface comprises generating an interface depicting a scene of the environment comprising a plurality of different elements associated with the plurality of different constraints.

12. The computer-implemented method of claim 10 , wherein:

generating the user interface comprises generating an interface depicting the at least one trajectory.

13. The computer-implemented method of claim 1 , wherein the motion plan is generated, determined, or selected through an interactive linear quadratic regulator based on the plurality of different constraints.

14. The computer-implemented method of claim 1 , wherein providing, through the user interface, the data indicative of the at least one constraint and the measure of the influence of the at least one constraint on the motion plan comprises:

receiving, through the user interface, user input indicative of a selection of the at least one point by a user; and

in response to the user input, providing data indicative of the at least one constraint and the sub measure of the influence of the at least one constraint on the motion plan at the at least one point.

15. An autonomous vehicle control system for controlling an autonomous vehicle, the autonomous vehicle control system comprising:

one or more processors; and

one or more non-transitory computer-readable media storing instructions that are executable by the one or more processors to cause the autonomous vehicle control system to perform operations, the operations comprising:

receiving data indicating a motion plan comprising at least one trajectory of an autonomous vehicle through an environment, wherein the at least one trajectory comprises a plurality of different points, wherein the motion plan is generated, determined, or selected based at least in part on a plurality of different constraints associated with the environment;

determining for at least one point of the plurality of different points, a sub measure of an influence of at least one of the plurality of different constraints on the motion plan at the at least one point, wherein a measure of the influence of the at least one constraint is indicative of a respective contribution of the at least one constraint to a generation, a determination, or a selection of the motion plan;

refining one or more instructions associated with the generation, the determination, or the selection of the motion plan based on the measure of the influence of the at least one constraint; and

instructing the autonomous vehicle to move in accordance with one or more motion plans that are generated, determined, or selected based on the one or more refined instructions.

16. The autonomous vehicle control system of claim 15 , wherein determining the sub measure of the influence of the at least one constraint at the at least one point comprises determining a respective measure of a respective influence of the at least one constraint relative to one or more other constraints of the plurality of different constraints.

17. The autonomous vehicle control system of claim 15 , wherein:

the environment comprises a plurality of different objects;

one or more of the plurality of different constraints are associated with the plurality of different objects; and

determining the sub measure of the influence of the at least one constraint at the at least one point comprises determining a contribution of at least one object of the plurality of different objects to the generation, the determination, or the selection of the motion plan.

18. The autonomous vehicle control system of claim 15 , wherein:

the environment comprises a plurality of different objects;

one or more of the plurality of different constraints are associated with a plurality of different actions the autonomous vehicle is instructed to take with respect to the plurality of different objects; and

determining the sub measure of the influence of the at least one constraint at the at least one point comprises determining a contribution of at least one action of the plurality of different actions to the generation, the determination, or the selection of the motion plan.

19. The autonomous vehicle control system of claim 18 , wherein the plurality of different actions instruct the autonomous vehicle to one or more of pass an object of the plurality of different objects, ignore an object of the plurality of different objects, queue behind an object of the plurality of different objects, maintain a position relative to an object of the plurality of different objects, maintain a distance between the autonomous vehicle and an object of the plurality of different objects, avoid an object of the plurality of different objects, or yield to an object of the plurality of different objects.

20. One or more non-transitory computer-readable media storing instructions that are executable by one or more processors to cause an autonomous vehicle control system to perform operations, the operations comprising:

receiving data indicating a motion plan comprising at least one trajectory of an autonomous vehicle through an environment, wherein the at least one trajectory comprises a plurality of different points, wherein the motion plan is generated, determined, or selected based at least in part on a plurality of different constraints associated with the environment;

determining for at least one point of the plurality of different points, a sub measure of an influence of at least one of the plurality of different constraints on the motion plan at the at least one point, wherein a measure of the influence of the at least one constraint is indicative of a respective contribution of the at least one constraint to a generation, a determination, or a selection of the motion plan;

refining one or more instructions associated with the generation, the determination, or the selection of the motion plan based on the measure of the influence of the at least one constraint; and

instructing the autonomous vehicle to move in accordance with one or more motion plans that are generated, determined, or selected based on the one or more refined instructions.

21. The one or more non-transitory computer-readable media of claim 20 , wherein determining the sub measure of the influence of the at least one constraint at the at least one point comprises determining a respective measure of a respective influence of the at least one constraint relative to one or more other constraints of the plurality of different constraints.

22. The one or more non-transitory computer-readable media of claim 20 , wherein:

the environment comprises a plurality of different objects;

one or more of the plurality of different constraints are associated with a plurality of different actions the autonomous vehicle is instructed to take with respect to the plurality of different objects; and

determining the sub measure of the influence of the at least one constraint at the at least one point comprises determining a contribution of at least one action of the plurality of different actions to the generation, the determination, or the selection of the motion plan.