Indoor localization of autonomous vehicles
Devices, systems, and methods are provided for indoor localization. A self-driving vehicle may detect a first fiducial marker located at a first location within a building, wherein the first fiducial marker comprises first fiducial marker information associated with the first location. The self-driving vehicle may retrieve the first fiducial marker information from the first fiducial marker. The self-driving vehicle may generate localization information of the self-driving vehicle based on the first fiducial marker information. The self-driving vehicle may utilize the localization information to transition to a second location within the building, wherein the second location comprises a second fiducial marker.
1. A self-driving vehicle, the self-driving vehicle comprising processing circuitry coupled to storage and a sensor system, the processing circuitry configured to:
detect, using a camera of the sensor system, a transitional fiducial marker located at a transition point corresponding to a building;
transition the processing circuitry from utilizing global positioning system (GPS) signals to utilizing one or more fiducial markers placed within the building for in-building navigation, using information retrieved from the transitional fiducial marker;
detect, using the camera of the sensor system, a first fiducial marker of the one more fiducial markers, wherein the first fiducial marker is located at a first location within the building;
retrieve, from the first fiducial marker, first fiducial marker information associated with the first location and transform information associated with a second location corresponding to a second fiducial marker of the one more fiducial markers, wherein the transform information is used by the self-driving vehicle to determine its pose relative to the second location;
generate localization information of the self-driving vehicle based on the first fiducial marker information; and
transition the self-driving vehicle to the second location within the building based on the localization information and the transform information.
2. The self-driving vehicle of claim 1 , wherein the transform information includes transformation matrices that describe rotation and translation of the self-driving vehicle with respect to the second location.
3. The self-driving vehicle of claim 1 , wherein the first fiducial marker is located in the line of sight of the self-driving vehicle.
4. The self-driving vehicle of claim 1 , wherein the second fiducial marker is located in the line of sight of the self-driving vehicle.
5. The self-driving vehicle of claim 1 , wherein the first fiducial marker information comprises global positioning system (GPS) information of the first location, a floor number of the building, coordinates of the fiducial marker, elevation of the fiducial marker, or a map location of the fiducial marker.
6. The self-driving vehicle of claim 1 , wherein retrieving the first fiducial marker information comprises the processing circuitry further configured to:
capture an image of the first fiducial marker;
analyze the image of the first fiducial marker; and
decode the first fiducial marker information of the first fiducial marker.
7. The self-driving vehicle of claim 1 , wherein the processing circuitry is further configured to calculate a distance from the self-driving vehicle to the first fiducial marker.
8. The self-driving vehicle of claim 1 , wherein the processing circuitry is further configured to:
detect that the second fiducial marker is moving away from the line of sight of the self-driving vehicle as the self-driving vehicle transitions from the second location to a third location;
detect a third fiducial marker of the one more fiducial markers located at the second location of the building, wherein the third fiducial marker is in the line of sight of the self-driving vehicle, and wherein the third fiducial marker comprises third fiducial marker information associated with the second location.
9. A method comprising:
detecting, using a camera of a sensor system of a self-driving vehicle, a transitional fiducial marker located at a transition point corresponding to a building;
transitioning a processing circuitry of the self-driving vehicle from utilizing global positioning system (GPS) signals to utilizing one or more fiducial markers placed within the building for in-building navigation, using information retrieved from the transitional fiducial marker;
detecting, using the camera of the sensor system of the self-driving vehicle, a first fiducial marker of the one more fiducial markers, wherein the first fiducial marker is located at a first location within the building;
retrieving, from the first fiducial marker, first fiducial marker information associated with the first location and transform information associated with a second location corresponding to a second fiducial marker of the one more fiducial markers, wherein the transform information is used by the self-driving vehicle to determine its pose relative to the second location;
generating localization information of the self-driving vehicle based on the first fiducial marker information; and
transition the self-driving vehicle to the second location within the building based on the localization information and the transform information.
10. The method of claim 9 , wherein the transform information includes transformation matrices that describe rotation and translation of the self-driving vehicle with respect to the second location.
11. The method of claim 9 , wherein the first fiducial marker is located in the line of sight of the self-driving vehicle.
12. The method of claim 9 , wherein the second fiducial marker is located in the line of sight of the self-driving vehicle.
13. The method of claim 9 , wherein the first fiducial marker information comprises global positioning system (GPS) information of the first location, a floor number of the building, coordinates of the fiducial marker, elevation of the fiducial marker, or a map location of the fiducial marker.
14. The method of claim 9 , wherein retrieving the first fiducial marker information comprises:
capturing an image of the first fiducial marker;
analyzing the image of the first fiducial marker; and
decoding the first fiducial marker information of the first fiducial marker.
15. The method of claim 9 , further comprising calculate a distance from the self-driving vehicle to the first fiducial marker.
16. The method of claim 9 , further comprising:
detecting that the second fiducial marker is moving away from the line of sight of the self-driving vehicle as the self-driving vehicle transitions from the second location to a third location;
detecting a third fiducial marker of the one more fiducial markers located at the second location of the building, wherein the third fiducial marker is in the line of sight of the self-driving vehicle, and wherein the third fiducial marker comprises third fiducial marker information associated with the second location.
17. A non-transitory computer-readable medium storing computer-executable instructions which when executed by one or more processors of a self-driving vehicle result in performing operations comprising:
detecting, using a camera of a sensor system of the self-driving vehicle, a transitional fiducial marker located at a transition point corresponding to a building;
transitioning a processing circuitry of the self-driving vehicle from utilizing global positioning system (GPS) signals to utilizing one or more fiducial markers placed within the building for in-building navigation, using information retrieved from the transitional fiducial marker;
detecting, using the camera of the sensor system of the self-driving vehicle, a first fiducial marker of the one more fiducial markers, wherein the first fiducial marker is located at a first location within the building;
retrieving, from the first fiducial marker, first fiducial marker information associated with the first location and transform information associated with a second location corresponding to a second fiducial marker of the one more fiducial markers, wherein the transform information is used by the self-driving vehicle to determine its pose relative to the second location;
generating localization information of the self-driving vehicle based on the first fiducial marker information; and
transition the self-driving vehicle to the second location within the building based on the localization information and the transform information.
18. The non-transitory computer-readable medium of claim 17 , wherein the transform information includes transformation matrices that describe rotation and translation of the self-driving vehicle with respect to the second location.
19. The non-transitory computer-readable medium of claim 17 , wherein the first fiducial marker is located in the line of sight of the self-driving vehicle.
20. The non-transitory computer-readable medium of claim 17 , wherein the second fiducial marker is located in the line of sight of the self-driving vehicle.