LIDAR FAULT DETECTION SYSTEM
Aspects of the present disclosure involve systems, methods, and devices for fault detection in a Lidar system. A fault detection system obtains incoming Lidar data output by a Lidar system during operation of an AV system. The incoming Lidar data includes one or more data points corresponding to a fault detection target on an exterior of a vehicle of the AV system. The fault detection system accesses historical Lidar data that is based on data previously output by the Lidar system. The historical Lidar data corresponds to the fault detection target. The fault detection system performs a comparison of the incoming Lidar data with the historical Lidar data to identify any differences between the two sets of data. The fault detection system detects a fault condition occurring at the Lidar system based on the comparison.
1 - 20 . (canceled)
21 . An autonomous vehicle (AV) system for an autonomous vehicle, the AV system comprising:
a Light Detection and Ranging (Lidar) system comprising a plurality of channels, the Lidar system configured to output Lidar data indicative of objects reflecting laser signals emitted by the Lidar system;
one or more detection features on an exterior of the autonomous vehicle; and
one or more processors to perform operations comprising:
obtaining incoming Lidar data output by the Lidar system during operation of the AV system, the incoming Lidar data comprising at least one Lidar point corresponding to the one or more detection features;
obtaining, from a memory, historical Lidar data based on previous output of the Lidar system, the historical Lidar data comprising at least one historical Lidar point corresponding to the one or more detection features from the previous output of the Lidar system, the at least one historical Lidar point comprising at least one of a historical range value or a historical intensity value;
determining a condition at the Lidar system based on incoming data points of the incoming Lidar data with historical data points of the historical Lidar data; and
initiating a restricted-operation state based on determining the condition.
22 . The AV system of claim 21 , wherein determining the condition at the Lidar system comprises:
performing a comparison of the incoming data points of the incoming Lidar data with the historical data points of the historical Lidar data; and
determining a difference between the incoming Lidar data and the historical Lidar data based on the comparison.
23 . The AV system of claim 22 , wherein determining the condition further comprises:
determining that the difference between the incoming Lidar data and the historical Lidar data satisfies a threshold condition.
24 . The AV system of claim 22 , wherein the difference comprises one of:
a difference between the historical intensity value and an incoming intensity value; or a difference between the historical range value and an incoming range value.
25 . The AV system of claim 21 , wherein one or more operations of the AV system are restricted while the AV system is in the restricted-operation state.
26 . The AV system of claim 25 , wherein the restricted-operation state comprises stopping the autonomous vehicle at an available stopping location.
27 . The AV system of claim 21 , wherein the initiating of the restricted-operation state comprises providing one or more commands to the autonomous vehicle.
28 . The AV system of claim 21 , wherein the one or more detection features comprise a coating applied to the exterior of the autonomous vehicle.
29 . The AV system of claim 21 , wherein the one or more detection features comprise one or more markings that are visible within a field of view of the Lidar system.
30 . The AV system of claim 21 , wherein the operations further comprise:
determining that the autonomous vehicle is stopped at a location, wherein the one or more processors obtain the incoming Lidar data in response to determining that the autonomous vehicle is stopped at the location.
31 . The AV system of claim 30 , wherein the initiating of the restricted-operation state comprises:
causing the autonomous vehicle to remain stopped at the location until a remediation action is performed.
32 . The AV system of claim 30 , wherein:
the one or more detection features further comprise an actuatable component; and
the AV system actuates the actuatable component in response to determining that the autonomous vehicle is stopped.
33 . The AV system of claim 21 , wherein the condition includes one or more of: a damaged component, a dirty component, a dislodged component, a reduced or diminished intensity of laser signals emitted by the Lidar system, or a reduced sensitivity of a detector of the Lidar system.
34 . A method comprising:
obtaining incoming Light Detection and Ranging (Lidar) data output by a Lidar system during operation of an autonomous vehicle, the Lidar system comprising a plurality of channels and being configured to output Lidar data indicative of objects reflecting laser signals emitted by the Lidar system, the incoming Lidar data corresponding to one or more detection features on an exterior of the autonomous vehicle;
obtaining, from a memory, historical Lidar data based on previous output of the Lidar system, the historical Lidar data corresponding to the one or more detection features and comprising at least one of a historical range value or a historical intensity value;
determining a condition at the Lidar system based on the incoming Lidar data and the historical Lidar data; and
initiating a restricted-operation state for the autonomous vehicle based on determining the condition.
35 . The method of claim 34 , wherein determining the condition comprises:
performing a comparison of the incoming Lidar data with the historical Lidar data;
based on the comparison, determining a difference between the incoming Lidar data and the historical Lidar data; and
determining that the difference between the incoming Lidar data and the historical Lidar data satisfies a threshold condition.
36 . The method of claim 35 , wherein the difference comprises one of:
a difference between the historical intensity value and an incoming intensity value; or
a difference between the historical range value and an incoming range value.
37 . The method of claim 34 , wherein one or more operations of the autonomous vehicle are restricted while the autonomous vehicle is in the restricted-operation state.
38 . The method of claim 34 , further comprising:
determining that the autonomous vehicle is stopped at a location, wherein the obtaining of the incoming Lidar data is in response to determining that the autonomous vehicle is stopped at the location; and
causing the autonomous vehicle to remain stopped at the location.
39 . The method of claim 38 , wherein:
the one or more detection features further comprise an actuatable component; and
the method further comprises actuating the actuatable component in response to determining that the autonomous vehicle is stopped.
40 . A machine storage medium storing instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:
obtaining incoming Light Detection and Ranging (Lidar) data output by a Lidar system during operation of an autonomous vehicle, the Lidar system comprising a plurality of channels and being configured to output Lidar data indicative of objects reflecting laser signals emitted by the Lidar system, the incoming Lidar data corresponding to one or more detection features on an exterior of the autonomous vehicle;
obtaining, from a memory, historical Lidar data based on previous output of the Lidar system, the historical Lidar data corresponding to the one or more detection features, the historical Lidar data comprising at least one of a historical range value or a historical intensity value;
determining a condition at the Lidar system based on the incoming Lidar data and the historical Lidar data; and
initiating a restricted-operation state at the AV system based on determining the condition at the Lidar system.