Collaborative vehicle path generation

1. A method comprising:

receiving, at a device remote from an autonomous vehicle, a request for assistance and sensor data associated with an environment of the autonomous vehicle;

determining, based at least in part on the sensor data, two or more candidate trajectories, wherein the two or more candidate trajectories comprise separate instructions configured to actuate drive components of the autonomous vehicle;

displaying, at the device, a representation of the environment and the two or more candidate trajectories;

receiving, at the device, input identifying a proposed trajectory from among the two or more candidate trajectories; and

transmitting the proposed trajectory to the autonomous vehicle, the autonomous vehicle configured to determine a path for controlling the autonomous vehicle based at least in part on the proposed trajectory, wherein the path comprises a first control trajectory that the autonomous vehicle determines based at least in part on the proposed trajectory and a second control trajectory that is based at least in part on the first control trajectory.

2. The method of claim 1 , wherein:

transmitting the proposed trajectory to the autonomous vehicle comprises transmitting a weight associated with the proposed trajectory; and

the autonomous vehicle generates a set of candidate trajectories based at least in part on the sensor data and the weight and determines one of the set of candidate trajectories based at least in part on the weight.

3. The method of claim 1 , further comprising:

determining a second set of candidate trajectories based at least in part on the proposed trajectory, the second set of candidate trajectories comprising a start position associated with an end position of the proposed trajectory;

receiving input identifying a second proposed trajectory from among the second set of candidate trajectories; and

transmitting the second proposed trajectory to the autonomous vehicle, wherein the path is further based at least in part on the second proposed trajectory.

4. The method of claim 1 , further comprising:

receiving, from the autonomous vehicle, a second set of candidate trajectories generated by the autonomous vehicle based at least in part on the proposed trajectory;

receiving input identifying a second proposed trajectory from among the second set of candidate trajectories; and

transmitting the second proposed trajectory to the autonomous vehicle, wherein the path is further based at least in part on the second proposed trajectory.

5. The method of claim 1 , wherein determining the two or more candidate trajectories is based at least in part on at least one of object data or map data determined based at least in part on the sensor data.

6. The method of claim 1 , wherein the proposed trajectory identifies at least one of a region, a lane, a location, or a weight that is used as part of a search algorithm running on the autonomous vehicle to identify the path.

7. A system comprising:

one or more processors; and

a memory storing processor-executable instructions that, when executed by the one or more processors, cause the system to perform operations comprising:

receiving, at a device remote from an autonomous vehicle, a request for assistance, a trajectory for the autonomous vehicle, and data associated with an environment of the autonomous vehicle;

determining, at the device, based on the data and the trajectory, in response to receiving the request for assistance, a proposed trajectory, wherein the proposed trajectory comprises instructions for actuating a drive component of the autonomous vehicle; and

transmitting the proposed trajectory to the autonomous vehicle, wherein the autonomous vehicle is configured to determine a control trajectory based at least in part on the proposed trajectory.

8. The system of claim 7 , wherein the operations further comprise:

determining, by the one or more processors, a second set of candidate trajectories based at least in part on the proposed trajectory, the second set of candidate trajectories comprising a start position associated with an end position of the proposed trajectory; and

transmitting a second proposed trajectory to the autonomous vehicle, the second proposed trajectory being determined from among the second set of candidate trajectories.

9. The system of claim 7 , wherein the operations further comprise:

receiving, from the autonomous vehicle, a second set of candidate trajectories generated by the autonomous vehicle based at least in part on the proposed trajectory;

identifying a second proposed trajectory from among the second set of candidate trajectories; and

transmitting the second proposed trajectory to the autonomous vehicle.

10. The system of claim 7 , wherein the operations further comprise:

generating a plurality of proposed trajectories for the autonomous vehicle including the proposed trajectory;

wherein the proposed trajectory is determined, from among the plurality of proposed trajectories, based on a weighting associated with the trajectory of the autonomous vehicle received at the device.

11. The system of claim 7 , wherein the proposed trajectory is determined based at least in part on:

historic data associated with a vehicle in a similar environment as the autonomous vehicle; or

additional data that provides addition information regarding the environment than the data associated with the environment received from the autonomous vehicle.

12. One or more non-transitory computer-readable media storing processor-executable instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:

receiving first sensor data from one or more sensors associated with an autonomous vehicle and a target location;

determining, based at least in part on the first sensor data and the target location, a first trajectory;

determining a confidence score associated with the first trajectory is less than a threshold;

transmitting, based at least in part on determining that the confidence score is less than the threshold, to a remote computing device, a request for teleoperator input;

receiving, from the remote computing device, a proposed trajectory comprising first instructions configured to actuate drive components of the autonomous vehicle;

receiving second sensor data from the one or more sensors associated with the autonomous vehicle;

determining, based at least in part on the second sensor data, a second trajectory; and

determining a control trajectory based at least in part on the proposed trajectory and the second trajectory, the control trajectory comprising second instructions configured to actuate the drive components.

13. The one or more non-transitory computer-readable media of claim 12 , wherein:

the operations further comprise receiving a weight associated with the proposed trajectory; and

determining the control trajectory comprises:

determining a cost associated with the control trajectory based at least in part on the weight; and

determining the control trajectory from a set of trajectories based at least in part on the cost.

14. The one or more non-transitory computer-readable media of claim 13 , wherein determining the control trajectory is based at least in part on a tree search.

15. The one or more non-transitory computer-readable media of claim 12 , wherein the operations further comprise:

transmitting a set of trajectories from the autonomous vehicle to the remote computing device, wherein the request for teleoperator input comprises the set of trajectories generated by the autonomous vehicle; and

wherein the proposed trajectory is one of the set of trajectories sent to the remote computing device.

16. The one or more non-transitory computer-readable media of claim 12 , wherein the operations further comprise:

at least one of:

receiving, from the remote computing device, a third trajectory; or

determining the second trajectory based at least in part on the control trajectory,

wherein the third trajectory comprises a start position associated with an end position of the control trajectory.

17. The one or more non-transitory computer-readable media of claim 12 , wherein the first trajectory is different from the second trajectory.

18. The one or more non-transitory computer-readable media of claim 12 , wherein the control trajectory is different than the proposed trajectory.

19. The one or more non-transitory computer-readable media of claim 12 , wherein the proposed trajectory identifies at least one of a region, a lane, a location, or a weight that is used as part of a search algorithm executed by the autonomous vehicle to identify the control trajectory.

20. The one or more non-transitory computer-readable media of claim 12 , wherein the control trajectory is generated at the remote computing device.