Detecting and responding to sirens
The technology relates to detecting and responding to emergency vehicles. This may include using a plurality of microphones to detect a siren noise corresponding to an emergency vehicle and to estimate a bearing of the emergency vehicle. This estimated bearing is compared to map information to identify a portion of roadway on which the emergency vehicle is traveling. In addition, information identifying a set of objects in the vehicle's environment as well as characteristics of those objects is received from a perception system is used to determine whether one of the set of objects corresponds to the emergency vehicle. How to respond to the emergency vehicle is determined based on the estimated bearing and identified road segments and the determination of whether one of the set of objects corresponds to the emergency vehicle. This determined response is then used to control the vehicle in an autonomous driving mode.
1. An autonomous vehicle comprising:
a plurality of time-synchronized microphones;
a classifier configured to:
distinguish siren noise emanated by an emergency vehicle from sounds other than the siren noise detected by the plurality of time-synchronized microphones based on amplitude and timing of the detected sounds, and
estimate characteristics of the emergency vehicle; and
one or more processors operatively coupled to the plurality of time-synchronized microphones and the classifier, the one or more processors being configured to control the autonomous vehicle based on the estimated characteristics of the emergency vehicle.
2. The autonomous vehicle of claim 1 , wherein the estimated characteristics include an estimated bearing of the emergency vehicle.
3. The autonomous vehicle of claim 2 , wherein spacing between the time-synchronized microphones corresponds to a function of an expected wavelength of a siren noise that occurs in a geographic area in which the autonomous vehicle is used.
4. The autonomous vehicle of claim 3 , wherein the function is one half of a wavelength of the siren noise.
5. The autonomous vehicle of claim 2 , wherein the estimated bearing is computed as a function of frequency, amplitude and time, so that different ones of the detected sounds that have similar frequency content, but different bearings, can be distinguished from one another.
6. The autonomous vehicle of claim 1 , wherein the estimated characteristics include an estimated relative velocity of the emergency vehicle.
7. The autonomous vehicle of claim 1 , wherein the estimated characteristics include an estimated range of the emergency vehicle.
8. A method, comprising;
detecting, by one or more processors via a plurality of time-synchronized microphones of an autonomous vehicle, a siren noise;
detecting, by the one or more processors via a perception system of the autonomous vehicle, flashing lights of an emergency vehicle at a time when the siren noise is detected;
estimating, by the one or more processors, characteristics of the emergency vehicle based on the detected siren noise and the detected flashing lights; and
controlling, by the one or more processors, an autonomous vehicle based on the estimated characteristics of the emergency vehicle.
9. The method of claim 8 , wherein the autonomous vehicle is controlled to pull onto a shoulder area when the emergency vehicle moves toward the autonomous vehicle.
10. The method of claim 8 , wherein the autonomous vehicle is controlled to stop before an intersection when the emergency vehicle moves toward the intersection.
11. The method of claim 8 , wherein the autonomous vehicle is controlled to make a turn based on a location of the autonomous vehicle relative to a location of the emergency vehicle.
12. The method of claim 8 , wherein the autonomous vehicle is controlled to continue on a current trajectory based on a location of the autonomous vehicle relative to a location of the emergency vehicle.
13. The method of claim 8 , wherein when the emergency vehicle is located behind an object, the flashing lights of the emergency vehicle are occluded from being detected by the perception system of the autonomous vehicle.
14. The method of claim 8 , wherein the characteristics include an estimated relative velocity of the emergency vehicle.
15. The method of claim 8 , wherein the characteristics include an estimated range to the emergency vehicle.
16. An autonomous vehicle comprising;
a plurality of time-synchronized microphones;
a perception system; and
one or more processors operably coupled to the plurality of time-synchronized microphones and the perception system, the one or more processors being configured to:
detect a siren noise via the plurality of time-synchronized microphones;
detect flashing lights of an emergency vehicle at a time when the siren noise is detected via the perception system;
estimate characteristics of the emergency vehicle; and
control the autonomous vehicle based on the estimated characteristics of the emergency vehicle.
17. The autonomous vehicle of claim 16 , wherein the autonomous vehicle is controlled to pull onto a shoulder area when the emergency vehicle moves toward the autonomous vehicle.
18. The autonomous vehicle of claim 16 , wherein the autonomous vehicle is controlled to stop before an intersection when the emergency vehicle moves toward the intersection.
19. The autonomous vehicle of claim 16 wherein the autonomous vehicle is controlled to make a turn based on a location of the autonomous vehicle relative to a location of the emergency vehicle.
20. The autonomous vehicle of claim 16 , wherein the autonomous vehicle is controlled to continue on a current trajectory based on a location of the autonomous vehicle relative to a location of the emergency vehicle.