Autonomous vehicle hybrid simulation testing

1. A computer-implemented method of autonomous vehicle testing, comprising:

obtaining, by a computing system comprising one or more computing devices, simulated perception data indicative of one or more simulated states of at least one simulated object within a surrounding environment of an autonomous vehicle,

wherein the computing system comprises a perception system and a prediction system, and wherein the simulated perception data is obtained via the prediction system and the perception system is disabled, wherein when the perception system is disabled the computing system is prevented from perceiving the surrounding environment based on sensor data:

determining, by the prediction system of the computing system, one or more predicted future locations of the at least one simulated object within the surrounding environment of the autonomous vehicle based at least in part on the simulated perception data:

determining, by the computing system, a motion of the autonomous vehicle based at least in part on the one or more predicted future locations of the at least one simulated object within the surrounding environment of the autonomous vehicle; and

causing, by the computing system, the autonomous vehicle to travel in accordance with the determined motion of the autonomous vehicle through the surrounding environment of the autonomous vehicle.

2. The computer-implemented method of claim 1 , wherein determining, by the computing system, the motion of the autonomous vehicle comprises:

determining, by the computing system, a motion plan for the autonomous vehicle based at least in part on the one or more predicted future locations of the at least one simulated object within the surrounding environment of the autonomous vehicle.

3. The computer-implemented method of claim 2 , wherein causing, by the computing system, the autonomous vehicle to travel in accordance with the determined motion of the autonomous vehicle through the surrounding environment of the autonomous vehicle comprises:

causing, by the computing system, the autonomous vehicle to travel in accordance with the motion plan for the autonomous vehicle.

4. The computer-implemented method of claim 1 , wherein the one or more simulated states of the at least one simulated object are indicative of one or more locations of the at least one simulated object within the surrounding environment of the autonomous vehicle at one or more respective times.

5. The computer-implemented method of claim 1 , wherein the at least one simulated object is configured to move within the surrounding environment of the autonomous vehicle.

6. The computer-implemented method of claim 1 , wherein obtaining the simulated perception data comprises:

obtaining, by the computing system, the simulated perception data from one or more remote computing devices; and

storing, by the computing system, the simulated perception data in an accessible memory onboard the autonomous vehicle.

7. The computer-implemented method of claim 1 , further comprising:

providing, by the computing system to one or more remote computing devices that are remote from the autonomous vehicle, feedback data associated with the autonomous vehicle.

8. The computer-implemented method of claim 7 , wherein the feedback data comprises at least one of one or more predicted future locations of the at least one simulated object or data messages associated with one or more systems onboard the autonomous vehicle.

9. A computing system for autonomous vehicle testing, comprising:

one or more processors; and

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

obtaining simulated perception data indicative of one or more simulated states of at least one simulated object within a surrounding environment of an autonomous vehicle, wherein the computing system comprises a perception system and a prediction system, and wherein the simulated perception data is obtained via the prediction system and the perception system is disabled, wherein when the perception system is disabled the computing system is prevented from perceiving the surrounding environment based on sensor data;

determining one or more predicted future locations of the at least one simulated object within the surrounding environment of the autonomous vehicle based at least in part on the simulated perception data;

determining a motion plan for the autonomous vehicle based at least in part on the one or more predicted future locations of the at least one simulated object within the surrounding environment of the autonomous vehicle; and

causing the autonomous vehicle to travel in accordance with the motion plan through the surrounding environment of the autonomous vehicle.

10. The computing system of claim 9 , wherein the surrounding environment of the autonomous vehicle is a testing environment.

11. The computing system of claim 10 , wherein the operations further comprise:

providing, to one or more remote computing devices that are remote from the autonomous vehicle, feedback data associated with the autonomous vehicle within the testing environment.

12. The computing system of claim 9 , wherein the one or more simulated states of the at least one simulated object are indicative of one or more locations of the at least one simulated object within the surrounding environment of the autonomous vehicle at one or more respective times.

13. The computing system of claim 9 , wherein the one or more simulated states of the at least one simulated object are indicative of at least one of a classification of the at least one simulated object or a heading of the at least one simulated object.

14. The computing system of claim 9 , wherein the simulated perception data indicates that the at least one simulated object is configured to be reactive to the motion of the autonomous vehicle.

15. A computer-implemented method comprising:

providing, by a computing system comprising one or more computing devices to an autonomous vehicle, simulated perception data indicative of a first simulated state of a simulated object within a surrounding environment of an autonomous vehicle,

wherein the autonomous vehicle comprises a perception system and a prediction system, and wherein the simulated perception data is obtained via the prediction system and the perception system is disabled, wherein when the perception system is disabled the computing system is prevented from perceiving the surrounding environment based on sensor data;

obtaining, by the computing system, vehicle data from the autonomous vehicle indicative of an action to be performed by the autonomous vehicle; and

determining, by the computing system based on the vehicle data, a second simulated state of the simulated object.

16. The computer-implemented method of claim 15 , wherein the vehicle data comprises data indicative of a motion plan of the autonomous vehicle.

17. The computer-implemented method of claim 16 , wherein the determining, by the computing system based on the vehicle data, the second simulated state of the simulated object comprises:

determining, by the computing system, the second simulated state of the simulated object to avoid an intersection with the motion plan of the autonomous vehicle.

18. The computer-implemented method of claim 15 , further comprising:

obtaining, by the computing system, data indicative of a state of another object within the surrounding environment; and

determining, by the computing system based on the data indicative of the state of the other object, the second simulated state of the simulated object.

19. The computer-implemented method of claim 1 , wherein the one or more simulated states of the at least one simulated object comprises at least one first simulated state, and wherein determining the motion of the autonomous vehicle comprises:

determining, by the computing system, a first motion plan for the autonomous vehicle based at least in part on the one or more predicted future locations of the at least one simulated object within the surrounding environment of the autonomous vehicle;

obtaining, by the computing system, adjusted simulated perception data indicative of at least one second simulated state of the at least one simulated object, wherein the at least one second simulated state of the at least one simulated object is different from the at least one first simulated state and based, at least in part, on the first motion plan for the autonomous vehicle; and

determining, by the computing system, the motion of the autonomous vehicle based at least in part on the at least one second simulated state of the at least one simulated object.