MIT researchers develop drone fleet system for SAR
Researchers from the MIT in the US have developed an autonomous system that will allow a fleet of drones to collaboratively search under dense forest canopies using only onboard computation and wireless communication.
Researchers from the Massachusetts Institute of Technology (MIT) in the US have developed an autonomous system that will allow a fleet of drones to collaboratively search under dense forest canopies using only onboard computation and wireless communication.
The paper will be presented at the International Symposium on Experimental Robotics conference next week. The system would have the drones equipped with laser-range finders for position estimation, localisation, and path planning, meaning that as each separate drone covered ground it could create a 3D map of the terrain. Algorithms would let the fleet know what ground had not been covered.
“Essentially, we’re replacing humans with a fleet of drones to make the search part of the search-and-rescue process more efficient,” said first author Yulun Tian, a graduate student in the Department of Aeronautics and Astronautics.
Though not within the current system, the paper proposes that the drones would be equipped with object detection, meaning that missing persons could be automatically detected, and their locations tagged by a done.
The system has been tested in multiple simulations and once in an actual forested area, when two drones mapped a 20-metre square area in around five minutes. In their paper, the researchers argue that their method helps drones to cover a greater area faster when compared to the traditional method.