Guiding drones by information gain
This work addresses gas source detection for environmental monitoring, presenting an incremental improvement over existing methods.
This study tackled the problem of estimating gas source locations and emission rates using drones by comparing two sampling strategies: infotaxis and deep reinforcement learning, with the latter showing superior performance in non-isotropic plume environments.
The accurate estimation of locations and emission rates of gas sources is crucial across various domains, including environmental monitoring and greenhouse gas emission analysis. This study investigates two drone sampling strategies for inferring source term parameters of gas plumes from atmospheric measurements. Both strategies are guided by the goal of maximizing information gain attained from observations at sequential locations. Our research compares the myopic approach of infotaxis to a far-sighted navigation strategy trained through deep reinforcement learning. We demonstrate the superior performance of deep reinforcement learning over infotaxis in environments with non-isotropic gas plumes.