OVERVIEW

Monitoring environmental phenomena by distributed sensor sampling confronts the challenge of unpredictable variability in the spatial distribution of phenomena often coupled with demands for a high spatial sampling rate. The introduction of actuation-enabled robotics sensors permits a system to optimize the sampling distribution through runtime adaptation. However, such systems must efficiently dispense sampling points or otherwise suffer from poor temporal response. In this research, we propose and characterize an Adaptive Sampling system. In our approach, as the robotic sensor acquires measurement samples of the environment, it builds a model of the phenomenon and based on incremental optimization process where the robot supports a continuous, iterative process of collecting samples with maximal coverage in the design space builds the environmental model. This model is further used for predicting sampling point locations that contribute the greatest certainty regarding the phenomenon and sampling the environment based on a combined measure of information gain and navigation and sampling cost.

PEOPLE

FACULTY

Prof. Mark Hansen
Prof. Deborah Estrin
Prof. Bill Kaiser
Prof. Mani Srivastava
Prof. Gaurav S. Sukhatme

STUDENTS

Mohammad Rahimi