Collaborative vehicle guidance

1. A system comprising:

one or more processors; and

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

determining, by a planning component of an autonomous vehicle, a first reference trajectory;

determining an event associated with the first reference trajectory;

determining a cost associated with the first reference trajectory;

determining if the cost meets or exceeds a cost threshold;

sending, based at least in part on the event and the cost meeting or exceeding the cost threshold, a request for guidance to a remote computing device, wherein the request for guidance comprises a confidence level associated with the first reference trajectory;

receiving, based at least in part on the request and from the remote computing device, a second reference trajectory, wherein the second reference trajectory is determined based at least in part on the confidence level;

generating, based at least in part on the first reference trajectory, the cost, and the second reference trajectory, a candidate trajectory; and

controlling the autonomous vehicle based at least in part on the candidate trajectory.

2. The system of claim 1 , the operations further comprising:

receiving sensor data of an environment captured by a sensor of the autonomous vehicle, the sensor data associated with a first time; and

sending the sensor data to the remote computing device;

wherein the second reference trajectory is based at least in part on the sensor data and indicates an acceleration for the autonomous vehicle and a steering for the autonomous vehicle to navigate in the environment at a second time after the first time.

3. The system of claim 1 , wherein the second reference trajectory is based at least in part on a capability of the autonomous vehicle to navigate in an environment, wherein the capability of the autonomous vehicle is based at least in part on kinematic information or dynamic information associated with the autonomous vehicle.

4. The system of claim 1 , wherein the second reference trajectory is based at least in part on at least one of a rate-controlled acceleration input or a rate-controlled steering input.

5. The system of claim 1 , the operations further comprising:

receiving, from the autonomous vehicle, sensor data indicating an object in an environment of the autonomous vehicle; and

determining, based at least in part on the sensor data and the object, at least one of an acceleration threshold, a velocity threshold, or a timing threshold associated with the autonomous vehicle navigating through the environment;

wherein the request for guidance comprises at least one of the acceleration threshold, the velocity threshold, or the timing threshold; and

wherein the second reference trajectory is determined based at least in part on the at least one of the acceleration threshold, the velocity threshold, or the timing threshold.

6. A method comprising:

determining, by a planning component of a vehicle, a first reference trajectory;

determining an event associated with the first reference trajectory;

determining a cost associated with the first reference trajectory;

determining if the cost meets or exceeds a cost threshold;

sending, based at least in part on the event and on the cost meeting or exceeding the cost threshold, a request for guidance from the vehicle navigating in an environment to a remote computing device, wherein the request for guidance comprises a confidence level associated with the first reference trajectory;

receiving, from the remote computing device and based at least in part on the request for guidance, one or more second reference trajectories for the vehicle to follow in the environment, wherein at least one of the one or more second reference trajectories is determined based at least in part on the confidence level;

generating, by the planning component of the vehicle and based at least in part on the first reference trajectory, the cost, and the one or more second reference trajectories, a trajectory to navigate the vehicle in the environment, wherein the trajectory is different from the first reference trajectory and the one or more second reference trajectories received from the remote computing device; and

controlling the vehicle based at least in part on the trajectory.

7. The method of claim 6 , wherein at least one of the one or more second reference trajectories is based at least in part on at least one of a rate-controlled acceleration input or a rate-controlled steering input.

8. The method of claim 7 , wherein:

the rate-controlled acceleration input is based at least in part on an acceleration capability associated with navigating the vehicle in the environment; and

the rate-controlled steering input is based at least in part on a steering capability associated with navigating the vehicle in the environment.

9. The method of claim 6 , wherein determining the trajectory is further based at least in part on at least one of a reference cost, a steering cost, an acceleration cost, or an obstacle cost associated with at least one of the one or more second reference trajectories.

10. The method of claim 6 , further comprising:

determining a rate-control threshold for use by the remote computing device based at least in part on sensor data associated with the vehicle; and

sending, to the remote computing device, the rate-control threshold to cause at least one of the one or more second reference trajectories to be determined based at least in part on the rate-control threshold.

11. The method of claim 6 , wherein at least one of the one or more second reference trajectories comprises an acceleration rate and a steering rate, the method further comprising:

determining, based at least in part on the acceleration rate associated with the one of the one or more second reference trajectories, an acceleration cost for the trajectory to navigate the vehicle;

determining, based at least in part on the steering rate associated with the one of the one or more second reference trajectories, a steering cost for the trajectory to navigate the vehicle; and

navigating the vehicle in the environment based at least in part on the acceleration cost and the steering cost.

12. The method of claim 6 , the method further comprising: determining an event, wherein the request for guidance is based at least in part on the event, wherein the event comprises at least one of a potential collision, an obstacle, or a road closure.

13. The method of claim 6 , further comprising:

receiving sensor data of the environment captured by a sensor of the vehicle; and

sending the sensor data to the remote computing device,

wherein at least one of the one or more second reference trajectories is based at least in part on the sensor data.

14. The method of claim 6 , further comprising:

detecting an event in the environment based at least in part on sensor data captured from a sensor of the vehicle; and

determining that the event impacts an ability of the vehicle to navigate to a destination,

wherein:

sending the request for guidance comprises sending the confidence level associated with the ability of the vehicle to navigate to the destination, and

the at least one of the one or more second reference trajectories is based at least in part on the confidence level.

15. The method of claim 6 , wherein at least one of the one or more second reference trajectories is based at least in part on one or more of a kinematic or a dynamic constraint of the vehicle to navigate in the environment.

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

determining, by a planning component of a vehicle, a first reference trajectory;

determining a cost associated with the first reference trajectory;

determining if the cost meets or exceeds a cost threshold;

sending, based at least in part on the cost meeting or exceeding the cost threshold, a request for guidance from the vehicle navigating in an environment, wherein the request for guidance comprises a confidence level associated with the first reference trajectory;

receiving, from a remote computing device and based at least in part on the request for guidance, a second reference trajectory for the vehicle to follow in the environment, wherein the second reference trajectory is determined based on at least in part on the confidence level;

generating, by the planning component of the vehicle and based at least in part on the first reference trajectory, the cost, and the second reference trajectory, a trajectory to navigate the vehicle in the environment; and

controlling the vehicle based at least in part on the trajectory.

17. The one or more non-transitory computer-readable media of claim 16 , wherein the second reference trajectory is based at least in part on at least one of a rate-controlled acceleration input or a rate-controlled steering input.

18. The one or more non-transitory computer-readable media of claim 16 , wherein the second reference trajectory is based at least in part on a kinematic or a dynamic constraint of the vehicle to navigate in the environment.

19. The one or more non-transitory computer-readable media of claim 16 , wherein determining the trajectory is further based at least in part on at least one of a reference cost, a steering cost, an acceleration cost, or an obstacle cost associated with the second reference trajectory.