Detecting and responding to sirens

1. A method of detecting and responding to emergency vehicles, the method comprising:

using, by one or more processors, a plurality of microphones arranged at different locations on a vehicle to detect a siren noise corresponding to an emergency vehicle;

using, by the one or more processors, output from the plurality of microphones to estimate a bearing, a range and a relative velocity of a source of the detected siren noise;

comparing, by the one or more processors, the estimated bearing to map information to identify a portion of a roadway on which the emergency vehicle is traveling;

determining, by the one or more processors, whether one vehicle of a plurality of vehicles within range of one or more sensors of a perception system of the vehicle corresponds to the emergency vehicle by determining information including at least one of a heading, location or relative velocity of each of the plurality of vehicles and, estimating a likelihood of each of the plurality of vehicles being the source of the detected siren noise by comparing the determined information of each of the plurality of vehicles to the estimated bearing, range and relative velocity of the source of the detected siren noise;

determining, by the one or more processors, how to respond to the emergency vehicle based on the estimated bearing and the identified portion of the roadway and the estimated likelihoods of each of the plurality of vehicles being the source of the siren noise; and

controlling, by the one or more processors, the vehicle in an autonomous driving mode based on the determination of how to respond to the emergency vehicle.

2. The method of claim 1 , further comprising using output from the plurality of microphones over time to estimate the range of the source of the detected siren noise.

3. The method of claim 1 , further comprising using output from the plurality of microphones over time to estimate the relative velocity of the source of the detected siren noise.

4. The method of claim 1 , wherein controlling the vehicle includes changing from a first lane to a second lane.

5. The method of claim 1 , wherein controlling the vehicle includes pulling the vehicle over onto a shoulder area.

6. The method of claim 1 , wherein controlling the vehicle includes continuing on a current trajectory of the vehicle.

7. The method of claim 1 , wherein controlling the vehicle further includes decreasing a speed of the vehicle.

8. A method of detecting and responding to emergency vehicles, the method comprising:

using, by one or more processors, a plurality of microphones arranged at different locations on a vehicle to detect a siren noise corresponding to an emergency vehicle;

using, by the one or more processors, output from the plurality of microphones to estimate a bearing, a range and a relative velocity of a source of the detected siren noise;

comparing, by the one or more processors, the estimated bearing to map information to identify a portion of a roadway on which the emergency vehicle is traveling;

receiving, from a perception system of the vehicle having one or more sensors, information identifying a set of objects in the vehicle's environment as well as characteristics of the set of objects, the set of objects including a plurality of vehicles, the characteristics for each of the plurality of vehicles including at least one of a heading, location or relative velocity;

determining based on the received information, by the one or more processors, whether one of the plurality of vehicles corresponds to the emergency vehicle based on the characteristics of the set of objects, including estimating a likelihood of each of the plurality of vehicles being the source of the detected siren noise by comparing the characteristics of each of the plurality of vehicles to the estimated bearing, range and relative velocity of the source of the detected siren noise;

determining, by the one or more processors, how to respond to the emergency vehicle based on the estimated bearing, the identified portion, and the determination of whether the one of plurality of vehicles corresponds to the emergency vehicle according to the estimated likelihoods of each of the plurality of vehicles being the source of the siren noise; and

controlling, by the one or more processors, the vehicle in an autonomous driving mode based on the determination of how to respond to the emergency vehicle.

9. The method of claim 8 , further comprising using output from the plurality of microphones over time to estimate the range of the source of the detected siren noise.

10. The method of claim 8 , further comprising using output from the plurality of microphones over time to estimate the relative velocity of the source of the detected siren noise.

11. The method of claim 8 , further comprising comparing, by the one or more processors, the estimated bearing to map information to identify a portion of roadway on which the emergency vehicle is traveling, and wherein determining how to respond to the emergency vehicle is further based on the estimated bearing and the portion of roadway.

12. The method of claim 8 , further comprising identifying a first likelihood that each given vehicle of the plurality of vehicles is the emergency vehicle based on the characteristics of that given vehicle, and wherein determining whether one of the plurality of vehicles corresponds to the emergency vehicle is further based on any first likelihoods.

13. The method of claim 8 , further comprising identifying a second likelihood that each given vehicle of the plurality of vehicles is not the emergency vehicle based on the characteristics of that given vehicle, and wherein determining whether one of the plurality of vehicles corresponds to the emergency vehicle is further based on any second likelihoods.

14. The method of claim 8 , wherein controlling the vehicle includes stopping at an intersection when the vehicle would otherwise have right of way to proceed through the intersection.

15. A system for detecting and responding to emergency vehicles, the system comprising one or more processors configured to:

use a plurality of microphones arranged at different locations on a vehicle to detect a siren noise corresponding to an emergency vehicle;

use output from the plurality of microphones over time to estimate a bearing, a range and a relative velocity of a source of the detected siren noise;

compare the estimated bearing to map information to identify a portion of roadway on which the emergency vehicle is traveling;

receive, from a perception system of the vehicle having one or more sensors, information identifying a set of objects in the vehicle's environment as well as characteristics of the set of objects, the set of objects including a plurality of vehicles, the characteristics for each of the plurality of vehicles including at least one of a heading, location or relative velocity;

determine based on the received information whether one of the plurality of vehicles corresponds to the emergency vehicle based on the characteristics of the set of objects, including estimation of a likelihood of each of the plurality of vehicles being a source of the detected siren noise by comparison of the characteristics of each of the plurality of vehicles to the estimated bearing, range and relative velocity of the source of the detected siren noise;

determine how to respond to the emergency vehicle based on the estimated bearing, the portion of roadway, and the determination of whether one of the plurality of vehicles corresponds to the emergency vehicle according to the estimated likelihoods of each of the plurality of vehicles being the source of the siren noise; and

control the vehicle in an autonomous driving mode based on the determination of how to respond to the emergency vehicle.

16. The system of claim 15 , wherein the one or more processors are further configured to use output from the plurality of microphones over time to estimate the range of the source of the detected siren noise.

17. The system of claim 15 , wherein the one or more processors are further configured to use output from the plurality of microphones over time to estimate the relative velocity of the source of the detected siren noise.

18. The system of claim 15 , further comprising the vehicle.