Detection of particulate matter in autonomous vehicle applications
Aspects and implementations of the present disclosure address shortcomings of the existing technology by enabling lidar-assisted segmentation and identification of particulate matter in autonomous vehicle (AV) applications, by: obtaining, by a sensing system of the AV, a plurality of return points, each return point having one or more velocity values and one or more coordinates of a reflecting region that reflects a signal emitted by the sensing system, identifying, in view of the one or more velocity values of each of a first set of the return points of the plurality of return points, that the first set of the return points is associated with a particulate matter in an environment of the AV, and causing a driving path of the AV to be determined in view of the particulate matter.
1. A method comprising:
obtaining, by a sensing system of an autonomous vehicle (AV), a plurality of return points, each return point comprising one or more velocity values and one or more coordinates of a reflecting region that reflects a signal emitted by the sensing system;
identifying, in view of the one or more velocity values of each of a first set of the return points of the plurality of return points, that the first set of the return points is associated with a particulate matter in an environment of the AV; and
causing a driving path of the AV to be determined in view of the particulate matter.
2. The method of claim 1 , wherein the sensing system of the AV comprises a coherent light detection and ranging device (lidar), the signal emitted by the sensing system comprises a phase-modulated or a frequency-modulated electromagnetic wave, and the one or more velocity values is a component of a velocity of the reflecting region along a direction from a transmitter of the sensing system to the reflecting region.
3. The method of claim 2 , wherein the coherent lidar is a frequency-modulated continuous-wave lidar.
4. The method of claim 1 , further comprising:
identifying, in view of fitting the one or more velocity values and the one or more coordinates of each of a second set of the return points to a rigid-body equation, that the second set of the return points is associated with a rigid object.
5. The method of claim 4 , wherein identifying that the second set of the return points is associated with the rigid object comprises:
identifying the second set of the return points as a cluster in a multi-dimensional space whose dimensions comprise the one or more velocity values and the one or more coordinates; and
identifying that the second set of the return points satisfies a clustering criterion; and wherein identifying that the first set of the return points is associated with the particulate matter comprises:
identifying that the first set of the return points does not satisfy the clustering criterion.
6. The method of claim 1 , wherein identifying that the first set of the return points is associated with the particulate matter comprises:
identifying that the one or more velocity values of the first set of the return points represent a disordered distribution of velocities.
7. The method of claim 1 , further comprising:
identifying, using the one or more velocity values of the first set of the return points, a wind velocity.
8. The method of claim 1 , wherein each return point further comprises an intensity value, and wherein the method further comprises:
identifying, in view of the intensity value for at least some of the first set of the return points, a type of the particulate matter.
9. The method of claim 8 , where the type of the particulate matter is one of mist, fog, snow, or dust.
10. The method of claim 1 , further comprising:
determining a first temporal intensity profile of an optical sensing signal reflected from the particulate matter; and
estimating a visibility range of the environment of the AV, in view of the first temporal intensity profile and a second temporal intensity profile of an optical sensing signal output by the sensing system of the AV.
11. A system comprising:
a sensing system of an autonomous vehicle (AV), the sensing system to:
obtain a plurality of return points, each return point comprising one or more velocity values and one or more coordinates of a reflecting region that reflects a signal emitted by the sensing system; and a perception system of the AV, the perception system to:
identify, in view of the one or more velocity values of each of a first set of the return points of the plurality of return points, that the first set of the return points is associated with a particulate matter in an environment of the AV; and
cause a driving path of the AV to be determined in view of the particulate matter.
12. The system of claim 11 , wherein the sensing system of the AV comprises a coherent light detection and ranging device (lidar), the signal emitted by the sensing system comprises a phase-modulated or a frequency-modulated electromagnetic wave, and the one or more velocity values is a component of a velocity of the reflecting region along a direction from a transmitter of the sensing system to the reflecting region.
13. The system of claim 11 , wherein the perception system is further to:
identify, in view of fitting the one or more velocity values and the one or more coordinates of each of a second set of the return points to a rigid-body equation, that the second set of the return points is associated with a rigid object.
14. The system of claim 11 , wherein to identify that the first set of the return points is associated with the particulate matter the perception system is to identify that the one or more velocity values of the first set of the return points represent a disordered distribution of velocities.
15. The system of claim 11 , wherein the perception system is further to:
identify, using the one or more velocity values of the first set of the return points, a wind velocity.
16. The system of claim 11 , wherein each return point further comprises an intensity value, and wherein the perception system is further to:
identify, in view of the intensity value for at least some of the first set of the return points, a type of the particulate matter.
17. The system of claim 11 , wherein the plurality of return points is obtained using signals reflected by a radar unit of the sensing system.
18. A non-transitory computer-readable medium having instructions stored thereon that, when executed by a computing device, cause the computing device to:
obtain, by a sensing system of an autonomous vehicle (AV), a plurality of return points, each return point comprising one or more velocity values and one or more coordinates of a reflecting region that reflects a signal emitted by the sensing system; and
identify, by a perception system of the AV and in view of the one or more velocity values of each of a first set of the return points of the plurality of return points, that the first set of the return points is associated with a particulate matter in an environment of the AV; and
cause a driving path of the AV to be determined in view of the particulate matter.
19. The non-transitory computer-readable medium of claim 18 , wherein to identify that the first set of the return points is associated with the particulate matter the instructions are to cause the computing device to identify that the one or more velocity values of the first set of the return points represent a disordered distribution of velocities.
20. The non-transitory computer-readable medium of claim 18 , wherein the instructions are further to cause the computing device to:
identify, using the one or more velocity values of the first set of the return points, a wind velocity.
21. The non-transitory computer-readable medium of claim 18 , wherein each return point further comprises an intensity value, and wherein the instructions are further to cause the computing device to:
identify, in view of the intensity value for at least some of the first set of the return points, a type of the particulate matter.