Distributed drone flight path builder system
Drones have become ubiquitous in performing risky and labor intensive areal tasks cheaply and safely. To allow them to be autonomous, their flight plan needs to be pre-built for them. Existing works do not precalculate flight paths but instead focus on navigation through camera based image processing techniques, genetic or geometric algorithms to guide the drone during flight. That makes flight navigation complex and risky. We present automated flight plan builder DIFPL which pre-builds flight plans for drones to survey a large area. The flight plans are built for subregions and fed into drones which allow them to navigate autonomously. DIFPL employs distributed paradigm on Hadoop MapReduce framework. Distribution is achieved by processing sections or subregions in parallel. Experiments performed with network and elevation datasets validate the efficiency of DIFPL in building optimal flight plans.
1. A method to generate a flight plan for an area to be surveyed, the method comprising:
identifying a plurality of subregions of an area to be surveyed;
constructing, based on network line and elevation data associated with the plurality of subregions, a flight plan portion for each of the plurality of subregions; and
storing a first subset of the flight plan portions in a memory of a first drone so as to enable autonomous navigation by the first drone within the area to be surveyed.
2. The method of claim 1 , including storing a second subset of the flight plan portions in a memory of a second drone, so as to enable autonomous navigation by the second drone within the area to be surveyed.
3. The method of claim 2 , including identifying the first drone within which to store the first subset of flight plan portions based on capabilities of the first drone, and identifying the second run within which to store the second subset of the flight plan portions based on capabilities of the second drone, wherein the capabilities of the first and second drones are different.
4. The method of claim 1 , wherein the constructing of the flight plan portion for each of the plurality of subregions is distributed within a MapReduce framework.
5. The method of claim 1 , including minimizing the number of subregions by merging boundary regions included in the plurality of subregions after constructing the flight plan portions for the plurality of subregions.
6. A system comprising:
at least one processor; and
at least one memory storing instructions that, when executed by the at least one processor, cause the at least one processor to:
identify a plurality of subregions of an area to be surveyed;
construct, based on network line and elevation data associated with the plurality of subregions, a flight plan portion for each of the plurality of subregions; and
store a first subset of the flight plan portions in a memory of a first drone so as to enable autonomous navigation by the first drone within the area to be surveyed.
7. The system of claim 6 , including storing a second subset of the flight plan portions in a memory of a second drone, so as to enable autonomous navigation by the second drone within the area to be surveyed.
8. The system of claim 7 , including identifying the first drone within which to store the first subset of flight plan portions based on capabilities of the first drone, and identifying the second run within which to store the second subset of the flight plan portions based on capabilities of the second drone, wherein the capabilities of the first and second drones are different.
9. The system of claim 6 , wherein the constructing of the flight plan portion for each of the plurality of subregions is distributed within a MapReduce framework.
10. The system of claim 6 , including minimizing the number of subregions by merging boundary regions included in the plurality of subregions after constructing the flight plan portions for the plurality of subregions.
11. A non-transitory computer-readable storage medium, the computer-readable storage medium storing instructions that, when executed by a computer, cause the computer to:
identify a plurality of subregions of an area to be surveyed;
construct, based on network line and elevation data associated with the plurality of subregions, a flight plan portion for each of the plurality of subregions; and
store a first subset of the flight plan portions in a memory of a first drone so as to enable autonomous navigation by the first drone within the area to be surveyed.
12. The computer-readable storage medium of claim 11 , including storing a second subset of the flight plan portions in a memory of a second drone, so as to enable autonomous navigation by the second drone within the area to be surveyed.
13. The computer-readable storage medium of claim 12 , including identifying the first drone within which to store the first subset of flight plan portions based on capabilities of the first drone, and identifying the second run within which to store the second subset of the flight plan portions based on capabilities of the second drone, wherein the capabilities of the first and second drones are different.
14. The computer-readable storage medium of claim 11 , wherein the constructing of the flight plan portion for each of the plurality of subregions is distributed within a MapReduce framework.
15. The computer-readable storage medium of claim 11 , including minimizing the number of subregions by merging boundary regions included in the plurality of subregions after constructing the flight plan portions for the plurality of subregions.