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. A method for detecting and responding to an emergency vehicle, the method comprising:
using, by one or more processors, a plurality of microphones arranged at different locations on a first vehicle to detect siren noise emanated by a second vehicle, the first vehicle being configured to operate in an autonomous driving mode;
estimating, by the one or more processors, which distance range of a plurality of distance ranges is most likely to include an actual distance between the first vehicle and the second vehicle;
determining, by the one or more processors, how the first vehicle should react to the second vehicle based on the estimated distance range; and
when it is determined that the first vehicle should react to the second vehicle, controlling, by the one or more processors in the autonomous driving mode, the first vehicle to react to the second vehicle.
2. The method of claim 1 , wherein the plurality of distance ranges are equal in size.
3. The method of claim 1 , wherein each of the plurality of distance ranges is associated with a respective likelihood value.
4. The method of claim 1 , further comprising:
determining, by the one or more processors, whether the distance range that is estimated to be most likely to include the actual distance meets a threshold likelihood value,
wherein determining how the first vehicle should react to the second vehicle is based on the distance range that is estimated to be most likely to include the actual distance meeting the threshold likelihood value.
5. The method of claim 1 , wherein the determining how the first vehicle should react includes determining whether the second vehicle is too far away to react to.
6. The method of claim 1 , further comprising:
estimating, by the one or more processors, a range rate which indicates how fast the siren noise is getting louder or softer,
wherein controlling the first vehicle to react to the second vehicle is based on the estimated range rate.
7. The method of claim 1 , further comprising:
estimating, by the one or more processors, a probability distribution over possible relative velocities of the second vehicle using the siren noise and timing collected over time,
wherein controlling the first vehicle to react to the second vehicle is based on an estimated velocity of the second vehicle determined based on the estimated probability distribution.
8. The method of claim 1 , wherein the first vehicle is controlled to react to the second vehicle by pulling over onto a shoulder area of a road.
9. The method of claim 1 , wherein the first vehicle is controlled to react to the second vehicle by stopping or slowing down.
10. A method for detecting and responding to an emergency vehicle, the method comprising:
using, by one or more processors, a plurality of microphones arranged at different locations on a first vehicle to detect siren noise emanated by a second vehicle, the first vehicle being configured to operate in an autonomous driving mode;
estimating, by the one or more processors, which velocity range of a plurality of velocity ranges is most likely to include an actual velocity of the second vehicle relative to the first vehicle;
determining, by the one or more processors, how the first vehicle should react to the second vehicle based on the estimated velocity range; and
when it is determined that the first vehicle should react to the second vehicle, controlling, by the one or more processors in the autonomous driving mode, the first vehicle to react to the second vehicle.
11. The method of claim 10 , wherein the estimated velocity range indicates how fast the second vehicle is moving towards the first vehicle or how fast the second vehicle is moving away from the first vehicle.
12. The method of claim 10 , wherein the estimated velocity range includes a plurality of different ranges of velocities.
13. The method of claim 12 , wherein each of the different ranges of velocities is associated with a respective likelihood value.
14. The method of claim 10 , further comprising:
determining, by the one or more processors, whether the estimated velocity range meets a threshold likelihood value,
wherein determining how the first vehicle should react to the second vehicle is based on the estimated velocity range meeting the threshold likelihood value.
15. The method of claim 10 , wherein the determining how the first vehicle should react includes determining whether the second vehicle is too far away to react to.
16. The method of claim 10 , wherein the first vehicle is controlled to react to the second vehicle by pulling over onto a shoulder area of a road.
17. The method of claim 10 , wherein the first vehicle is controlled to react to the second vehicle by stopping or slowing down.
18. The method of claim 10 , wherein the plurality of velocity ranges are equal in size.
19. A vehicle configured to operate in an autonomous driving mode and to detect and respond to an emergency vehicle, the vehicle comprising:
a plurality of microphones arranged at different locations on the vehicle to detect siren noise emanated by another vehicle; and
one or more processors coupled to the plurality of microphones, where the one or more processors are configured to:
estimate which distance range of a plurality of distance ranges is most likely to include an actual distance between the vehicle and the other vehicle;
determine how the vehicle should react to the other vehicle based on the estimated distance range; and
when it is determined that the vehicle should react to the other vehicle, control the vehicle to react to the other vehicle.
20. The vehicle of claim 19 , wherein the one or more processors are further configured to:
estimate a range rate that indicates how fast the siren noise is getting louder or softer,
wherein the vehicle is controlled to react to the other vehicle based on the estimated range rate.
21. The vehicle of claim 19 , wherein the one or more processors are further configured to:
estimate a probability distribution over possible relative velocities of the other vehicle using the siren noise and timing collected over time,
wherein the vehicle is controlled to react to the other vehicle based on an estimated velocity of the other vehicle determined based on the estimated probability distribution.
22. The vehicle of claim 19 , wherein the plurality of distance ranges are equal in size.