Adaptive Robotic Search and Sampling of Sparse Natural Phenomena

Jessica E. Todd, Ph.D., 2024
Dana Yoerger, Advisor

Autonomous robots are increasingly being used in the field of scientific exploration and data acquisition. Intelligent autonomous robots, capable of online adaptive planning, are seeing wide use in underwater field mapping and agricultural monitoring. However the ma- jority of these approaches utilize belief maps generated over easily observable phenomena such a temperature, salinity or tree coverage. Underwater and planetary science can often involve phenomena that are ‘expensive’ to observe, discrete, and sparsely distributed. For example coral disease can be visually detected when hovering close to the reef, due to light attenuation underwater, putting the robot at risk of collision with obstacles, or organisms. Subsurface water on Mars can only be detected from a landed system on the surface, due to the short range of the detectors. When operating in a resource-constrained environment, such as a limited battery life, expensive sensing actions can eat up the resource budget thus limiting the range of area that can be explored. This thesis aims to address this challenge by combining semantic ’substrates’ in the environment with hierarchical probabilistic modelling which maps substrate distributions to the underlying phenomena of interest. By observing substrates over a wide field of view, a robot can be guided to regions known to be associ- ated with the phenomena of interest. This problem is formulated as a partially-observable Markov decision process (POMDP) referred to as the Search and Sample problem. This thesis proposes two algorithmic contributions to the field of adaptive path planning to ad- dress two scenarios within this framework. In the first scenario, we assume the robot has a priori knowledge about the expected density of discrete targets in the various substrates, however is operating without prior knowledge of substrate distributions. We develop a novel multi-altitude planning method for seeking out targets by mixing low-altitude observations of discrete targets with high-altitude observations of the surrounding substrates. By using prior information about the distribution of targets across substrate types in combination with belief modelling over these substrates in the environment, high- altitude observations provide information that allows SASS to quickly guide the robot to areas with high target densities. In our second scenario, this a priori assumption is relaxed and the robot is now operating without strong prior knowledge of target density, or the relationship between tar- get and substrate. Drawing inspiration from the Species Distribution Modelling community, an hierarchical probabilistic model is developed using the Integrated Nested Laplace Ap- proximation framework, that enables online inference about expected target hotspots using

predicted substrate distributions. Model parameters are learned online to build a prediction over the discrete targets, and this is integrated into an anytime online planner to enable adaptive path planning. Both algorithms are extensively evaluated with both synthetic and real-world datasets. Additionally, through the course of addressing these two scenarios, two novel generative species-substrate model were developed that enable rapid simulation of synthetic worlds, with properties derived from real-world data. The development of these simulators allow the testing of path planners that aim to exploit natural correlations in spatial distributions that occur in the real world.