Abstract:
Mobile robots used for information gathering tasks rely on dense, predictive mapping of large-scale regions to determine where to take measurements. Current approaches to mapping commonly rely on Gaussian process regression to spatially correlate data, extrapolate from sparse samples, and estimate uncertainty. However, these approaches do not incorporate meaningful information about physical processes that contribute to the scientific observations being recorded, instead focusing on only predicting measurements or relying on black box expert-based systems to incorporate physically meaningful information.

The proposed work will develop physical process-informed mapping, a framework for integrating scientific knowledge about physical processes into mapping for mobile exploration robots. This approach will provide two advantages for exploration. First, the hierarchical statistical model underlying the mapping framework will be capable of providing predictions and uncertainty estimates for both the sensor measurements and the latent natural phenomenon driving these measurements in a dense, probabilistic manner. Second, the mapping approach will incorporate methods to measure and adjust the importance of various models of scientific knowledge, enabling learning about the conditions under which these models are more or less relevant to the latent phenomenon. Taken together, these improvements are expected to increase the predictive accuracy of mapping relative to the standard Gaussian process approach, as well as increasing the efficiency with which a mobile robot gains information when exploring.

Thesis Committee Members:
David Wettergreen, chair
Wennie Tabib
Mikael Kuusela
Terrence Fong, NASA Ames Research Center

More Information