Task 3.3: Control of Mobile Vehicles and Other Dynamic Assets

[Kumar, Mangharam, Pappas, Rosing]

Exploiting distributed localization techniques, in this task we will develop controllers that form and update belief states about the environment without prior detailed models. These methods will adaptively rely on observed data and will opportunistically exploit any available networked interactions across mobile platforms and with the cloud. The goal is to develop estimation algorithms to update belief states and decision-making algorithms that will guide mobile platforms to improve their belief states, thereby dramatically improving the ability of the TerraSwarm to develop total awareness.