Maintaining distance during vehicle interactions

1 . A method comprising:

determining, for a vehicle traversing an environment, a first path along which the vehicle is predicted to travel, the first path associated with a lane change maneuver from a first lane to a second lane;

determining, for an object traversing the environment, a second path along which the object is predicted to travel, the object comprising a further vehicle, the second path associated with the second lane, wherein after the lane change maneuver the vehicle is predicted to travel in the second lane ahead of the object;

determining a region of potential collision between the vehicle and the object based at least in part on the first path and the second path;

determining that the vehicle is in or will be in the region of potential collision first; and

based at least in part on determining that the vehicle is or will be in the region of potential collision first:

determining a stopping distance for at least the object from a location in the region of potential collision;

determining a current distance of at least the object from the location in the region of potential collision;

calculating a cost value based at least in part on the stopping distance and the current distance; and

controlling movement of the vehicle based at least in part on the cost value.

2 . The method of claim 1 , comprising:

determining a first position of the vehicle along the first path that is within a predefined distance to a first position of the object along the second path,

wherein the region of potential collision is determined based at least in part on the first positions.

3 . The method of claim 1 , wherein the region of potential collision is determined based at least in part on a predicted worst-case action by the one of the vehicle or the object.

4 . The method of claim 3 , wherein the predicted worst-case action comprises at least one of:

the vehicle or the object stopping in the region of potential collision; or

the object driving towards the vehicle at its current velocity.

5 . The method of claim 1 , wherein the stopping distance and the current distance are determined based at least in part on determining that the vehicle will be in the region first, and wherein the stopping distance and current distance are determined from a location on an edge of the region of potential collision.

6 . The method of claim 1 , wherein the stopping distance and the current distance are determined based at least in part on determining that the vehicle is in the region first, and wherein the stopping distance and the current distance are determined from a location occupied by the object.

7 . The method of claim 1 , comprising:

calculating a value indicating alignment of the vehicle and object based at least in part on the first path and the second path,

wherein the cost value is determined based at least in part on the value.

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

determining, for a vehicle traversing an environment, a first path along which the vehicle is predicted to travel;

determining, for an object traversing the environment, a second path along which the object is predicted to travel, the object comprising a further vehicle, the first path and second path associated with travel in a same lane direction, wherein the vehicle is predicted to be in front of the object with respect to the lane direction;

determining a region of potential collision between the vehicle and the object based at least in part on the first path and the second path;

determining that the vehicle is in or will be in the region of potential collision first; and

based at least in part on determining that the vehicle is or will be in the region of potential collision first:

determining a stopping distance for at least the object from a location in the region of potential collision;

determining a current distance of at least the object from the location in the region of potential collision;

calculating a cost value based at least in part on the stopping distance and the current distance; and

controlling movement of the vehicle based at least in part on the cost value.

9 . The computer-readable media of claim 8 , wherein the vehicle is controlled to perform at least one of the following actions based at least in part on the cost value:

decelerate to increase the current distance;

maintain a current velocity;

stop at a position on the first path before the region of potential collision;

emit a warning signal to the object; or

follow a third path having a lower cost value.

10 . The computer-readable media of claim 8 , wherein the instructions, when executed, cause the one or more processors to perform operations comprising:

determining a cost function based at least in part on the stopping distance, wherein the cost value is determined based on the cost function and the current distance and wherein the cost function comprises one or more of:

a safe stop cost function based on the stopping distance being a safe stopping distance associated with a maximum deceleration of the other of the vehicle or object; or

a comfort stop cost function based on the stopping distance being a comfort stopping distance associated with a deceleration of the other of the vehicle or object that is less than the maximum deceleration.

11 . The computer-readable media of claim 10 , wherein the cost function comprises a combination of the safe stop and comfort stop cost functions.

12 . The computer-readable media of claim 11 , wherein the cost function is a weighted combination of the safe stop and comfort stop cost functions, wherein the weighting is based at least in part on a direction of travel of the vehicle relative to the object.

13 . The computer-readable media of claim 10 , wherein the cost function comprises a linear portion and a quadratic portion.

14 . The computer-readable media of claim 8 , wherein the stopping distance and current distance are determined for the object, and are based on a reaction time for the object.