Detecting sensor degradation by actively controlling an autonomous vehicle
View Patent ↗Methods and systems are disclosed for determining sensor degradation by actively controlling an autonomous vehicle. Determining sensor degradation may include obtaining sensor readings from a sensor of an autonomous vehicle, and determining baseline state information from the obtained sensor readings. A movement characteristic of the autonomous vehicle, such as speed or position, may then be changed. The sensor may then obtain additional sensor readings, and second state information may be determined from these additional sensor readings. Expected state information may be determined from the baseline state information and the change in the movement characteristic of the autonomous vehicle. A comparison of the expected state information and the second state information may then be performed. Based on this comparison, a determination may be made as to whether the sensor has degraded.
1. An apparatus, comprising:
a computer-readable memory storing map information for a driving environment of an autonomous vehicle;
a laser sensor unit configured to detect a static object in the driving environment of the autonomous vehicle; and
one or more processors, in communication with the laser sensor unit and the computer-readable memory, the one or more processors configured to:
receive readings from the laser sensor unit relating to the static object, the readings including recorded laser points and corresponding received intensity values;
compare the received intensity values of the recorded laser points with stored intensity values corresponding to map laser points of the stored map information;
determine, based on the comparison, one or more deviation values; and
determine, based on the deviation values, whether the laser sensor unit has degraded.
2. The apparatus of claim 1 , wherein the received readings include geometry readings.
3. The apparatus of claim 2 , wherein comparing the recorded laser points with the map laser points comprises comparing position information.
4. The apparatus of claim 1 , wherein in determining the one or more deviation values, the one or more processors are configured to determine a number of recorded laser points that are different from the map laser points associated with the detailed map.
5. The apparatus of claim 1 , wherein the one or more processors are further configured to:
compare the deviation values with one or more corresponding deviation thresholds values; and
determine that the laser sensor has degraded when the deviation values meet or exceed the one or more deviation threshold values.
6. The apparatus of claim 1 , wherein the one or more processors are configured to perform the comparing of the recorded laser points with map laser points of the stored map information, determining the one or more deviation values, and determining whether the laser sensor unit has degraded separately for individual laser beams.
7. The apparatus of claim 6 , wherein the one or more processors are further configured to perform the comparing of the recorded laser points with map laser points of the stored map information, determining the one or more deviation values, and determining whether the laser sensor unit has degraded separately for the laser sensor unit as a whole.
8. A method, comprising:
receiving, with one or more processors, readings from a laser sensor unit, the readings relating to a static object in a driving environment of an autonomous vehicle, the readings including recorded laser points and corresponding received intensity values;
accessing a memory storing map information for the driving environment of the autonomous vehicle;
comparing, with the one or more processors, the received intensity values of the recorded laser points with stored intensity values corresponding to map laser points of the stored map information;
determining, with the one or more processors, based on the comparison, one or more deviation values; and
determining, with the one or more processors, based on the deviation values, whether the laser sensor unit has degraded.
9. The method of claim 8 , wherein the received readings include geometry readings.
10. The method of claim 9 , wherein comparing the recorded laser points with the map laser points comprises comparing position information.
11. The method of claim 8 , wherein determining the one or more deviation values comprises determining a number of recorded laser points that are different from the map laser points associated with the detailed map.
12. The method of claim 8 , further comprising:
comparing the deviation values with one or more corresponding deviation thresholds values; and
determining that the laser sensor unit has degraded when the deviation values meet or exceed the one or more deviation threshold values.
13. The method of claim 8 , wherein comparing the recorded laser points with map laser points of the stored map information, determining the one or more deviation values, and determining whether the laser sensor unit has degraded is performed separately for individual laser beams.
14. The method of claim 13 , further comprising comparing the recorded laser points with map laser points of the stored map information, determining the one or more deviation values, and determining whether the laser sensor unit has degraded for the laser sensor unit as a whole.
15. An autonomous vehicle, comprising:
a laser sensor unit configured to detect a static object in a driving environment of the autonomous vehicle; and
one or more processors, in communication with the laser sensor unit, the one or more processors configured to:
receive readings from the laser sensor unit relating to the static object, the readings including recorded laser points;
receive map information for the driving environment of the autonomous vehicle, the map information including map laser points and corresponding received intensity values;
compare the received intensity values of the recorded laser points with stored intensity values corresponding to map laser points;
determine, based on the comparison, one or more deviation values; and
determine, based on the deviation values, whether the laser sensor unit has degraded.
16. The autonomous vehicle of claim 15 , wherein the received readings include geometry readings, and wherein comparing the recorded laser points with the map laser points comprises comparing position information.
17. The autonomous vehicle of claim 15 , wherein in determining the one or more deviation values, the one or more processors are configured to determine a number of recorded laser points that are different from the map laser points associated with the detailed map.