Date of Award
Spring 5-31-2023
Document Type
Thesis (Undergraduate)
Department
Computer Science
First Advisor
Alberto Quattrini Li
Abstract
We introduce a framework that combines Gaussian Process models, robotic sensor measurements, and sampling data to predict spatial fields. In this context, a spatial field refers to the distribution of a variable throughout a specific area, such as temperature or pH variations over the surface of a lake. Whereas existing methods tend to analyze only the particular field(s) of interest, our approach optimizes predictions through the effective use of all available data. We validated our framework on several datasets, showing that errors can decline by up to two-thirds through the inclusion of additional colocated measurements. In support of adaptive sampling, this framework offers recommendations for sampling locations based on different objectives. Robotic adaptive sampling is essential in various applications such as environmental monitoring, underwater exploration, and resource management. This work, by leveraging all available data and increasing the number of fields used for prediction, contributes to robotic adaptive sampling research and supports the development of more effective robotic systems.
Recommended Citation
Nathan, Zachary, "Data-Optimized Spatial Field Predictions for Robotic Adaptive Sampling: A Gaussian Process Approach" (2023). Computer Science Senior Theses. 3.
https://digitalcommons.dartmouth.edu/cs_senior_theses/3
The project codebase including the GP models, API, experiments, and figures
Included in
Applied Statistics Commons, Artificial Intelligence and Robotics Commons, Data Science Commons
