LIDAR localization
A system including a processor and a memory, the memory including instructions to be executed by the processor to determine map data, determine uncalibrated LIDAR data, determine a location of a vehicle in the map data by combining the map data with the uncalibrated LIDAR data, and operate the vehicle based on the location of the vehicle in the map data.
1. A method, comprising:
determining map data;
determining uncalibrated LIDAR data by including reflectivity measurements corresponding to ground-plane return data and excluding measurements data corresponding to non-ground-plane return data;
determining a location of a vehicle in the map data by combining the map data with the uncalibrated LIDAR data; and
operating the vehicle based on the location of the vehicle in the map data.
2. The method of claim 1 , wherein determining the map data includes determining a first location with respect to the map data based on location sensors including GPS, INS, and odometry.
3. The method of claim 1 , further comprising determining the uncalibrated LIDAR data by orthogonally projecting reflectivity measurements onto a 2D grid.
4. The method of claim 3 , further comprising determining the uncalibrated LIDAR data by determining x and y gradients of the uncalibrated LIDAR data.
5. The method of claim 4 , further comprising determining the uncalibrated LIDAR data by combining x and y gradients of the uncalibrated LIDAR data from a plurality of LIDAR scans based on the location of the LIDAR scans.
6. The method of claim 5 , wherein the uncalibrated LIDAR data includes missing data encoded as infinity or NAN.
7. The method of claim 1 , wherein combining the map data with the uncalibrated LIDAR data includes matching the map data with the uncalibrated LIDAR data to determine registration between the map data with the uncalibrated LIDAR data by determining normalized mutual information over a set of neighborhood location/poses between the map data and the uncalibrated LIDAR data.
8. The method of claim 7 , further comprising determining the location of the vehicle with respect to the map data by updating the location by processing the registration between the map data and uncalibrated LIDAR data with an extended Kalman filter.
9. A system, comprising a processor; and
a memory, the memory including instructions to be executed by the processor to:
determine map data;
determine uncalibrated LIDAR data by including reflectivity measurements corresponding to ground-plane return data and excluding measurements data corresponding to non-ground-plane return data;
determine a location of a vehicle in the map data by combining the map data with the uncalibrated LIDAR data; and
operate the vehicle based on the location of the vehicle in the map data.
10. The processor of claim 9 , further programmed to determine the map data including determining a first location with respect to the map data based on location sensors including GPS, INS, and odometry.
11. The processor of claim 9 , further programmed to determine the uncalibrated LIDAR data by orthogonally projecting reflectivity measurements onto a 2D grid.
12. The processor of claim 11 , further programmed to determine the uncalibrated LIDAR data by determining x and y gradients of the uncalibrated LIDAR data.
13. The processor of claim 12 , further programmed to determine the uncalibrated LIDAR data by combining x and y gradients of the uncalibrated LIDAR data from a plurality of LIDAR scans based on the location of the LIDAR scans.
14. The processor of claim 13 , wherein the uncalibrated LIDAR data includes missing data encoded as infinity or NAN.
15. The processor of claim 9 , wherein combining the map data with the uncalibrated LIDAR data includes matching the map data with the uncalibrated LIDAR data to determine registration between the map data with the uncalibrated LIDAR data by determining normalized mutual information over a set of neighborhood location/poses between the map data and the uncalibrated LIDAR data.
16. The processor of claim 15 , further programmed to determine the location of the vehicle with respect to the map data by updating the location by processing the registration between the map data and uncalibrated LIDAR data with an extended Kalman filter.
17. A system, comprising
an uncalibrated LIDAR sensor operative to acquire uncalibrated LIDAR data;
a location sensors operative to acquire a first location;
vehicle components operative to operate a vehicle;
a processor; and
a memory, the memory including instructions to be executed by the processor to:
determine map data based on the first location;
determine uncalibrated LIDAR data by including reflectivity measurements corresponding to ground-plane return data and excluding measurements data corresponding to non-ground-plane return data;
determine a location of a vehicle in a second map by combining the map data with the uncalibrated LIDAR data; and
actuate vehicle components to operate the vehicle based on the location of the vehicle in the second map.
18. The system of claim 17 , wherein the first location is acquired by location sensors including GPS, INS, and odometry.