Non-centralised mutual control is key to a team of drones that can defend a place against attack, according to researchers in Saudi Arabia.
Performance of the scheme was judged in a capture-the-flag game, where the team of defender drones worked together within a defined area to intercept a human-controlled intruder drone and prevent it from reaching a specific place.
UAVs were custom-built and equipped with Wi-Fi for communication. “We designed a distributed architecture in which the drones coordinate based on local information and peer-to-peer communications,” said researcher Jeff Shamma at King Abdullah University of Science and Technology (KAUST)
Algorithms and protocols were intended to achieve an optimal level of peer-to-peer messaging, which needed to be not too much, not too little, and rapid reaction times, without too much heavy computation, according to KAUST. This allows the algorithm to work effectively in real time while the drones are chasing an intruder.
“Each of our drones makes its own plan based on a forecast of optimistic views of their team-mates’ actions and pessimistic views of the opponent’s actions,” said researcher Mohamed Abdelkader (pictured). “Since these forecasts may be inaccurate, each drone executes only a portion of its plan, then reassesses the situation before re-planning.”
The algorithm worked in both indoor and outdoor arenas under different attack scenarios, said KAUST, and it has been made available in open-source form as a test bed for other applications.
The team hopes to enable the drones to work in larger, outdoor areas and to improve the software by incorporating adaptive machine-learning techniques.
“A team of drones that can communicate among themselves provides a tool that could be used widely, for example, to improve security or capture images simultaneously over a large area,” said Abdelkader.