Object interaction prediction systems and methods for autonomous vehicles

1. A computer-implemented method comprising:

obtaining data associated with a first object and a second object within a surrounding environment of an autonomous vehicle,

wherein the first object comprises a first vehicle, a first pedestrian, or a first bicycle, and wherein the second object comprises a second vehicle, a second pedestrian, or a second bicycle;

generating a graph model, wherein the graph model comprises vertices indicative of respective trajectories of the first object or the second object and edges indicative of a dependency between the respective trajectories;

determining an interaction between the first object and the second object based at least in part on the graph model, the data associated with the first object and the second object, and at least one traffic rule;

determining, based at least in part on the interaction, a potential intersection between the respective trajectories of the first object and the second object;

determining, based at least in part on the potential intersection, a secondary interaction between the first object and the second object, the secondary interaction indicative of a modified predicted movement of the first object or a modified predicted movement of the second object that avoids the potential intersection; and

controlling motion for the autonomous vehicle based at least in part on the secondary interaction.

2. The computer-implemented method of claim 1 , wherein determining the interaction between the first object and the second object comprises:

determining the interaction between the first object and the second object based at least in part on a machine-learned model.

3. The computer-implemented method of claim 1 , wherein the traffic rule is associated with a geographic feature within the surrounding environment.

4. The computer-implemented method of claim 1 , wherein the interaction is based at least in part on one or more policies associated with at least one of a predicted movement of the first object or a predicted movement of the second object.

5. The computer-implemented method of claim 4 , wherein the one or more policies are associated with a scenario comprising yielding or acting at a traffic intersection.

6. The computer-implemented method of claim 1 , wherein determining the interaction between the first object and the second object comprises associating the first object with the second object.

7. The computer-implemented method of claim 1 , wherein the interaction between the first object and the second object is determined based at least in part on map data.

8. A computing system, comprising:

one or more processors; and

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

obtaining data associated with a first object and a second object within a surrounding environment of an autonomous vehicle,

wherein the first object comprises a first vehicle, a first pedestrian, or a first bicycle, and wherein the second object comprises a second vehicle, a second pedestrian, or a second bicycle;

generating a graph model, wherein the graph model comprises vertices indicative of respective trajectories of the first object or the second object and edges indicative of a dependency between the respective trajectories;

determining an interaction between the first object and the second object based at least in part on the graph model, the data associated with the first object and the second object, and at least one traffic rule;

determining, based at least in part on the interaction, a potential intersection between the respective trajectories of the first object and the second object;

determining, based at least in part on the potential intersection, a secondary interaction between the first object and the second object, the secondary interaction indicative of a modified predicted movement of the first object or a modified predicted movement of the second object that avoids the potential intersection; and

controlling motion for the autonomous vehicle based at least in part on the secondary interaction.

9. The computing system of claim 8 , wherein determining the motion for the autonomous vehicle based at least in part on the interaction between the first object and the second object comprises:

determining at least one of a trajectory, a speed, or an acceleration of the autonomous vehicle.

10. The computing system of claim 8 , wherein determining the interaction between the first object and the second object comprises:

determining the interaction between the first object and the second object based at least in part on a machine-learned model.

11. The computing system of claim 10 , wherein the machine-learned model is utilized to associate the first object with the second object.

12. The computing system of claim 8 , wherein the interaction between the first object and the second object is determined based at least in part on map data associated with the surrounding environment of the autonomous vehicle.

13. The computing system of claim 12 , wherein the map data is indicative of the traffic rule.

14. The computing system of claim 13 , wherein the traffic rule is associated with at least one of an intersection, a stop sign, a merge area, or a stop light.

15. An autonomous vehicle, comprising:

one or more processors; and

one or more tangible, non-transitory, computer readable media storing instructions that when executed by the one or more processors cause the autonomous vehicle to perform operations comprising:

obtaining data associated with a first object and a second object within a surrounding environment of the autonomous vehicle,

wherein the first object comprises a first vehicle, a first pedestrian, or a first bicycle, and wherein the second object comprises a second vehicle, a second pedestrian, or a second bicycle;

generating a graph model, wherein the graph model comprises vertices indicative of respective trajectories of the first object or the second object and edges indicative of a dependency between the respective trajectories;

determining an interaction between the first object and the second object based at least in part on the graph model, the data associated with the first object and the second object, and at least one traffic rule;

determining, based at least in part on the interaction, a potential intersection between the respective trajectories of the first object and the second object;

determining, based at least in part on the potential intersection, a secondary interaction between the first object and the second object, the secondary interaction indicative of a modified predicted movement of the first object or a modified predicted movement of the second object that avoids the potential intersection; and

controlling motion for the autonomous vehicle based at least in part on the secondary interaction.

16. The autonomous vehicle of claim 15 , wherein the interaction between the first object and the second object is determined based at least in part on map data associated with the surrounding environment of the autonomous vehicle.

17. The autonomous vehicle of claim 15 , wherein the interaction is determined based at least in part on a machine-learned model.

18. The autonomous vehicle of claim 15 , wherein the first object and the second object are in a follow-lead scenario.