Priority-based coverage path planning for Aerial Wireless Sensor Networks

Aerial Wireless Sensor Networks (AWSNs) are being increasingly used in search and rescue operations for locating victims stranded in disaster areas. The primary objective of such missions is to locate the victims as quickly as possible. As such, determining the optimal flight path for UAVs is very important. In this paper, we solve the coverage problem while optimising the time to find victim when number of victims in the disaster area is unknown. Path planning problem in weighted terrain is NP-Complete problem. Next we propose a heuristic based on Partially Observable Markov Decision Processes (POMDP). Using POMDP in this problem makes sense for two reasons, first we have partial knowledge of terrain and secondly the way POMDP maximises the reward in its transition function is requirement of our problem. We conduct extensive simulations and demonstrate that our solution can reduce the time to find all victims by up to 150% as compared to the state-of-the-art. We also show that our solution achieves full coverage of disaster area as compared to partial coverage of other algorithms.