Responding to emergency vehicles for autonomous vehicles
Sensor data identifying an emergency vehicle approaching the autonomous vehicle may be received. A predicted trajectory for the emergency vehicle may be received. Whether the autonomous vehicle is impeding the emergency vehicle may be determined based on the predicted trajectory and map information identifying a road on which the autonomous vehicle is currently traveling. Based on a determination that the autonomous vehicle is impeding the emergency vehicle, the autonomous vehicle may be controlled in an autonomous driving mode in order to respond to the emergency vehicle.
1. A method comprising:
determining, by one or more processors of an autonomous vehicle as an emergency vehicle approaches the autonomous vehicle, whether the autonomous vehicle will impede the emergency vehicle approaching the autonomous vehicle based on an available road width, a width of the emergency vehicle, and a buffer distance, wherein the available road width is a distance from a closest edge of a trajectory of the autonomous vehicle, across an opposing lane of traffic to a closest point on an object identified as a vehicle moving below a predetermined speed; and
responsive to determining that the autonomous vehicle will impede the emergency vehicle, controlling, by the one or more processors, the autonomous vehicle in an autonomous driving mode in order to respond to the emergency vehicle.
2. The method of claim 1 , wherein determining whether the autonomous vehicle will impede the emergency vehicle comprises determining whether the available road width is greater than the width of the emergency vehicle plus the buffer distance.
3. The method of claim 2 , wherein the available road width being less than or equal to the width of the emergency vehicle plus the buffer distance is indicative that the autonomous vehicle will impede the emergency vehicle.
4. The method of claim 2 , wherein determining whether the autonomous vehicle will impede the emergency vehicle further comprises, responsive to determining that the available road width is less than or equal to the width of the emergency vehicle plus the buffer distance, determining that the autonomous vehicle will impede the emergency vehicle.
5. The method of claim 1 , wherein determining whether the autonomous vehicle will impede the emergency vehicle comprises determining, by the one or more processors, the available road width based on map information identifying a road on which the autonomous vehicle and the emergency vehicle are currently traveling.
6. The method of claim 1 , wherein determining whether the autonomous vehicle will impede the emergency vehicle is further based on whether the emergency vehicle is approaching the autonomous vehicle from in front of or behind the autonomous vehicle.
7. The method of claim 1 , wherein determining whether the autonomous vehicle will impede the emergency vehicle is further based on a number of lanes of traffic of a road on which the autonomous vehicle and the emergency vehicle are currently traveling.
8. The method of claim 7 , wherein determining whether the autonomous vehicle will impede the emergency vehicle is further based on whether the road has only one lane of traffic going in a direction of the autonomous vehicle.
9. The method of claim 7 , wherein determining whether the autonomous vehicle will impede the emergency vehicle is further based on whether the road has an opposing lane of traffic.
10. A system comprising:
memory configured to store map information identifying a road on which an autonomous vehicle and an emergency vehicle are currently traveling; and
one or more processors coupled to the memory and configured to:
determine whether the autonomous vehicle will impede the emergency vehicle based on a predicted trajectory of the emergency vehicle approaching the autonomous vehicle and the map information; and
responsive to a determination that the autonomous vehicle will impede the emergency vehicle, control the autonomous vehicle in an autonomous driving mode to cause the autonomous vehicle to enter an intersection to an extent necessary to provide sufficient space for the emergency vehicle to pass the autonomous vehicle.
11. The system of claim 10 , wherein the one or more processors are further configured to determine whether the autonomous vehicle will impede the emergency vehicle further based on a plurality of heuristics.
12. The system of claim 10 , wherein the one or more processors are further configured to determine whether the autonomous vehicle will impede the emergency vehicle further based on one or more waypoints of a planned trajectory of the autonomous vehicle.
13. The system of claim 10 , wherein the one or more processors are configured to:
determine whether the predicted trajectory of the emergency vehicle includes the emergency vehicle entering an intended destination lane of a potential lane change of the autonomous vehicle; and
responsive to a determination that the predicted trajectory of the emergency vehicle includes the emergency vehicle entering the intended destination lane, prevent the potential lane change of the autonomous vehicle.
14. The system of claim 10 , wherein the one or more processors are configured to identify a pullover location for the autonomous vehicle such that the autonomous vehicle will not block the emergency vehicle or other traffic on the road.
15. The system of claim 10 , wherein the one or more processors are configured to control the autonomous vehicle in the autonomous driving mode to cause the autonomous vehicle to enter the intersection based on a maximum allowable braking limit of the autonomous vehicle.
16. The system of claim 10 , wherein the one or more processors are configured to move a virtual fence into the intersection based on a maximum allowable braking limit for the autonomous vehicle to provide sufficient space the emergency vehicle to pass the autonomous vehicle.