Method and system for accurate long term simultaneous localization and mapping with absolute orientation sensing
Described herein are embodiments of a method and system that uses a vertical or upward facing imaging sensor to compute vehicle attitude, orientation, or heading and combines the computed vehicle attitude, orientation, or heading with range bearing measurements from an imaging sensor, LiDAR, sonar, etc., to features in the vicinity of the vehicle to compute accurate position and map estimates.
1. An electronic mapping system comprising:
an upward facing sensor oriented to capture data in a direction perpendicular to a surface upon which the electronic mapping system travels;
a range bearing sensor; and
a processor in communication with the upward facing sensor and the range bearing sensor, the processor configured to:
determine an absolute orientation estimate of the electronic mapping system based upon first data received from the upward facing sensor, wherein the first data is indicative of a line feature of a building structure;
determine a location of local landmarks based upon second data received from the range bearing sensor;
determine a relative orientation estimate based on the location of the local landmarks;
fuse, using a Kalman filter, the absolute orientation estimate and the relative orientation estimate;
determine a location of the electronic mapping system based upon a result of the fuse of the absolute orientation estimate and the relative orientation estimate, and
create a new map of the building structure based only on the first data from the upward facing sensor and the second data from the range bearing sensor.
2. The electronic mapping system of claim 1 , wherein the line feature is of an edge of a light fixture or a part of a corrugated ceiling.
3. The electronic mapping system of claim 2 , wherein the upward facing sensor comprises a camera.
4. The electronic mapping system of claim 1 further comprising an inertial sensor, wherein the relative orientation estimate comprises a relative pose based upon a scan match, wherein the scan match comprises inputs of the second data and a third data received from the inertial sensor.
5. The electronic mapping system of claim 4 , wherein the processor configured to determine the location of the electronic mapping system comprises the processor configured to estimate an orientation of the electronic mapping system based on the fuse of the absolute orientation estimate and the relative orientation estimate.
6. The electronic mapping system of claim 5 , wherein the processor configured to determine the location of the electronic mapping system further comprises the processor configured to solve a least-squares optimization problem.
7. The electronic mapping system of claim 1 , wherein the processor is further configured to update the map based upon the location of the mapping system and the location of the local landmarks.
8. The electronic mapping system of claim 1 , wherein the processor is further configured to:
extract the line feature from the first data received from the upward facing sensor; and
determine an orientation angle of the extracted line feature,
wherein the absolute orientation estimate is with respect to the determined orientation angle.
9. An autonomous vehicle comprising:
an upward facing sensor oriented to capture data in a direction perpendicular to a surface upon which the autonomous vehicle travels;
a range bearing sensor; and
an electronic mapping system in communication with the upward facing sensor and the range bearing sensor, the electronic mapping system comprising a processor configured to:
determine an absolute orientation estimate of the autonomous vehicle based upon first data received from the upward facing sensor, wherein the first data is indicative of a line feature of a building structure;
determine a location of local landmarks based upon second data received from the range bearing sensor;
determine a relative orientation estimate based on the location of the local landmarks;
fuse, using a Kalman filter, the absolute orientation estimate and the relative orientation estimate;
determine a location of the autonomous vehicle based upon a result of the fuse of the absolute orientation estimate and the relative orientation estimate; and
create a new map of the building structure based only on the first data from the upward facing sensor and the second data from the range bearing sensor.
10. The autonomous vehicle of claim 9 , wherein the line feature is of an edge of a light fixture or a part of a corrugated ceiling.
11. The autonomous vehicle of claim 10 , wherein the upward facing sensor comprises a camera.
12. The autonomous vehicle of claim 9 further comprising an inertial sensor, wherein the relative orientation estimate comprises a relative pose based upon a scan match, wherein the scan match comprises inputs of the second data and a third data received from the inertial sensor.
13. The autonomous vehicle of claim 12 , wherein the processor configured to determine the location of the autonomous vehicle comprises the processor configured to estimate an orientation of the electronic mapping system based on the fuse of the absolute orientation estimate and the relative orientation estimate.
14. The autonomous vehicle of claim 13 , wherein the processor configured to determine the location of the electronic mapping system further comprises the processor configured to solve a least-squares optimization problem.
15. The autonomous vehicle of claim 9 , wherein the processor is further configured to update the map based upon the location of the autonomous vehicle and the location of the local landmarks.
16. A method for mapping implemented by an electronic mapping system, the method comprising:
determining an absolute orientation of the electronic mapping system based upon first data received from an upward facing sensor oriented to capture data in a direction perpendicular to a surface upon which the electronic mapping system travels, wherein the first data is indicative of a line feature of a building structure;
determining a location of local landmarks based upon second data received from a range bearing sensor;
determining a relative orientation estimate based on the location of the local landmarks;
fusing, using a Kalman filter, the absolute orientation estimate and the relative orientation estimate;
determining a location of the electronic mapping system based upon a result of fusing the absolute orientation estimate and the relative orientation estimate; and
creating a new map of the building structure based only on the first data from the upward facing sensor and the second data from the range bearing sensor.
17. The method of claim 16 , wherein the line feature is of an edge of a light fixture or a part of a corrugated ceiling.
18. The method of claim 16 , wherein the relative orientation estimate comprises a relative pose based upon a scan match, wherein the scan match comprises inputs of the second data and a third data received from an inertial sensor.
19. The method of claim 18 , wherein determining the location of the electronic mapping system comprises estimating an orientation of the electronic mapping system based on the fuse of the absolute orientation estimate and the relative orientation estimate.
20. The method of claim 19 , wherein determining the location of the electronic mapping system further comprises the processor configured to solve a least-squares optimization problem.
21. The method of claim 16 further comprising updating the map based upon the location of the mapping system and the location of the local landmarks.