Our oceans drive worldwide weather-climate systems; our rivers serve as nutrient conduits; and our marine ecosystems house the largest repository of biodiversity and mineral resources on the planet. Humans have relied on rivers, lakes, and oceans for transportation, energy generation, farming, and recreation throughout our history. And today, robots are critical tools in our stewardship of these resources. However, there are significant autonomy challenges when working in dynamic and uncertain environments like oceans and rivers. Robot dynamics are tightly coupled to those of the environment, while communication and localization are limited.

Control under these conditions can be exacting, but environmental dynamics may be harnessed to plan energy efficient paths and to maintain network connectivity. Networked robot teams can collect data to construct high fidelity models of the environmental dynamics which can be integrated into robot control and planning. Those same models can be used to guide robot control and sampling strategies to increase their predictive power. In this talk, I will present our vision of a smart ocean observational framework to improve forecasting of weather-climate systems, mitigation of contaminant dispersions, and coordination of maritime search and rescue and humanitarian efforts.