Online validation of LIDAR-to-LIDAR alignment and LIDAR-to-vehicle alignment
A LIDAR-to-LIDAR alignment system includes a memory and an autonomous driving module. The memory stores first and second points based on outputs of first and second LIDAR sensors. The autonomous driving module performs a validation process to determine whether alignment of the LIDAR sensors satisfy an alignment condition. The validation process includes: aggregating the first and second points in a vehicle coordinate system to provide aggregated LIDAR points; based on the aggregated LIDAR points, performing (i) a first method including determining pitch and roll differences between the first and second LIDAR sensors, (ii) a second method including determining a yaw difference between the first and second LIDAR sensors, or (iii) point cloud registration to determine rotation and translation differences between the first and second LIDAR sensors; and based on results of the first method, the second method or the point cloud registration, determining whether the alignment condition is satisfied.
1. A LIDAR-to-LIDAR alignment system comprising:
a memory configured to store (i) first points of data provided based on an output of a first LIDAR sensor, and (ii) second points of data provided based on an output of a second LIDAR sensor; and
an autonomous driving module configured to perform a validation process to determine whether alignment of the first LIDAR sensor and the second LIDAR sensor satisfy one or more alignment conditions, the validation process comprising
aggregating the first points of data and the second points of data in a vehicle coordinate system of a vehicle to provide aggregated LIDAR points, wherein the aggregating of the first points of data and the second points of data includes
performing point registration to map the first points of data at a first time in a coordinate system of the first LIDAR sensor at a second time,
aggregating the mapped first points of data from the first LIDAR sensor to provide first aggregated points,
performing point registration to map the second points of data at the first time in a coordinate system of the second LIDAR sensor at the second time, and
aggregating the mapped second points of data from the second LIDAR sensor to provide second aggregated points,
based on the aggregated LIDAR points, at least one of
performing a first method including determining pitch and roll differences between the first LIDAR sensor and the second LIDAR sensor,
performing a second method including determining a yaw difference between the first LIDAR sensor and the second LIDAR sensor, or
performing point cloud registration to determine rotation and translation differences between the first LIDAR sensor and the second LIDAR sensor,
based on results of at least one of the first method, the second method or the point cloud registration, determining whether the one or more alignment conditions are satisfied, and
in response to the one or more alignment conditions not being satisfied, recalibrating at least one of the first LIDAR sensor or the second LIDAR sensor.
2. The LIDAR-to-LIDAR alignment system of claim 1 , wherein the autonomous driving module is further configured to:
determine whether a plurality of enabling conditions are satisfied including two or more of
determining whether the vehicle is moving,
determining whether the vehicle is in a known location,
determining whether a velocity of the vehicle is greater than a predetermined velocity,
determining whether an acceleration rate of the vehicle is greater than a predetermined acceleration rate, or
determining whether a yaw rate is greater than a predetermined yaw rate; and
in response to the plurality of enabling conditions being satisfied, aggregate the first points of data and the second points of data.
3. The LIDAR-to-LIDAR alignment system of claim 1 , wherein the aggregating of the first points of data and the second points of data further includes:
mapping the first aggregated points to the vehicle coordinate system based on a rotation calibration value and a translation calibration value for the first LIDAR sensor; and
mapping the second aggregated points to the vehicle coordinate system based on a rotation calibration value and a translation calibration value for the second LIDAR sensor.
4. The LIDAR-to-LIDAR alignment system of claim 1 , wherein the aggregating of the first points of data and the second points of data includes:
mapping first points of data to the vehicle coordinate system based on a rotation calibration value and a translation calibration value for the first LIDAR sensor; and
mapping the second points of data to the vehicle coordinate system based on a rotation calibration value and a translation calibration value for the second LIDAR sensor.
5. The LIDAR-to-LIDAR alignment system of claim 1 , wherein the autonomous driving module is configured to:
based on aggregated LIDAR points, perform ground fitting and selecting to provide first selected points of the first LIDAR sensor in a ground area and second selected points of the second LIDAR sensor in the ground area; and
perform the first method based on the first selected points and the second selected points.
6. The LIDAR-to-LIDAR alignment system of claim 1 , wherein the autonomous driving module is configured to perform the first method and, based on results of the first method, determine whether the one or more alignment conditions are satisfied.
7. The LIDAR-to-LIDAR alignment system of claim 1 , wherein the autonomous driving module is configured to perform the second method, based on results of the second method, determine whether the one or more alignment conditions are satisfied.
8. The LIDAR-to-LIDAR alignment system of claim 1 , wherein the autonomous driving module is configured to perform the point cloud registration and, based on results of the point cloud registration, determine whether the one or more alignment conditions are satisfied.
9. The LIDAR-to-LIDAR alignment system of claim 1 , wherein the autonomous driving module is configured to perform the first method, the second method and the point cloud registration and, based on results of the first method, the second method and the point cloud registration, determine whether the one or more alignment conditions are satisfied.
10. The LIDAR-to-LIDAR alignment system of claim 1 , wherein the autonomous driving module is configured to, based on alignment results of the first LIDAR sensor to the vehicle and results of the second LIDAR sensor to the vehicle, calculate six degrees of freedom difference values between the first LIDAR sensor and the second LIDAR sensor.
11. A LIDAR-to-LIDAR alignment system comprising:
a memory configured to store (i) first points of data provided based on an output of a first LIDAR sensor, and (ii) second points of data provided based on an output of a second LIDAR sensor; and
an autonomous driving module configured to perform a validation process to determine whether alignment of the first LIDAR sensor and the second LIDAR sensor satisfy one or more alignment conditions, the validation process comprising aggregating the first points of data and the second points of data in a vehicle coordinate system to provide aggregated LIDAR points,
based on the aggregated LIDAR points, at least one of
performing a first method including determining pitch and roll differences between the first LIDAR sensor and the second LIDAR sensor,
performing a second method including determining a yaw difference between the first LIDAR sensor and the second LIDAR sensor, or
performing point cloud registration to determine rotation and translation differences between the first LIDAR sensor and the second LIDAR sensor,
based on results of at least one of the first method, the second method or the point cloud registration, determining whether the one or more alignment conditions are satisfied;
in response to the one or more alignment conditions not being satisfied, recalibrating at least one of the first LIDAR sensor or the second LIDAR sensor;
integrate results from one or more of the first method, the second method and the point cloud registration including determining a weighted sum of a vector of difference values for six degrees of freedom; and
in response to one or more of the difference values exceeding a predetermined threshold, at least one of (i) identifying one or more of the first LIDAR sensor and the second LIDAR sensor as suspicious, or (ii) recalibrating the one or more of the first LIDAR sensor and the second LIDAR sensor.
12. The LIDAR-to-LIDAR alignment system of claim 11 , wherein the autonomous driving module is configured to, based on knowing a transform from a first LIDAR sensor coordinate system to the vehicle coordinate system is accurate and the weighted sum of the vector of difference values, determine whether transform from a second LIDAR sensor coordinate system to the vehicle coordinate system is accurate.
13. A LIDAR-to-LIDAR alignment validation method comprising:
aggregating first points of data and second points of data in a vehicle coordinate system of a vehicle to provide aggregated LIDAR points, wherein the first points of data are provided based on an output of a first LIDAR sensor, and the second points of data are provided based on an output of a second LIDAR sensor, and wherein the aggregating of the first points of data and the second points of data includes:
performing point registration to map the first points of data at a first time in a coordinate system of the first LIDAR sensor at a second time,
aggregating the mapped first points of data from the first LIDAR sensor to provide first aggregated points,
performing point registration to map the second points of data at the first time in a coordinate system of the second LIDAR sensor at the second time,
aggregating the mapped second points of data from the second LIDAR sensor to provide second aggregated points,
mapping the first aggregated points to the vehicle coordinate system based on a rotation calibration value and a translation calibration value for the first LIDAR sensor, and
mapping the second aggregated points to the vehicle coordinate system based on a rotation calibration value and a translation calibration value for the second LIDAR sensor;
based on the aggregated LIDAR points, at least one of
performing a first method including determining pitch and roll differences between the first LIDAR sensor and the second LIDAR sensor,
performing a second method including determining a yaw difference between the first LIDAR sensor and the second LIDAR sensor, or
performing point cloud registration to determine rotation and translation differences between the first LIDAR sensor and the second LIDAR sensor;
based on results of at least one of the first method, the second method or the point cloud registration, determining whether one or more alignment conditions are satisfied; and
in response to the one or more alignment conditions not being satisfied, recalibrating at least one of the first LIDAR sensor or the second LIDAR sensor.
14. The method of claim 13 , further comprising:
determining whether a plurality of enabling conditions are satisfied including two or more of
determining whether the vehicle is moving,
determining whether the vehicle is in a known location,
determining whether a velocity of the vehicle is greater than a predetermined velocity,
determining whether an acceleration rate of the vehicle is greater than a predetermined acceleration rate, or
determining whether a yaw rate is greater than a predetermined yaw rate; and
in response to the plurality of enabling conditions being satisfied, aggregating the first points of data and the second points of data.
15. The method of claim 13 , further comprising:
based on aggregated LIDAR points, performing ground fitting and selecting to provide first selected points of the first LIDAR sensor in a ground area and second selected points of the second LIDAR sensor in the ground area; and
performing the first method based on the first selected points and the second selected points.
16. The method of claim 13 , further comprising performing the first method and the second method and, based on results of the first method and the second method, determining whether the one or more alignment conditions are satisfied.
17. The method of claim 13 , further comprising performing the point cloud registration and, based on results of the point cloud registration, determining whether the one or more alignment conditions are satisfied.
18. The method of claim 13 , further comprising performing the first method, the second method and the point cloud registration and, based on results of the first method, the second method and the point cloud registration, determine whether the one or more alignment conditions are satisfied.