The long-term operation of mobile robots demands efficient scene representations for high level Task and Motion Planning (TAMP). Recent work has proposed 3D scene graphs, which provide temporally consistent hierarchical abstractions of the environment. Research has been conducted on utilizing these 3D scene graphs for TAMP, but typically assumes the graph is constructed a priori. This work integrates Hydra-generated scene graphs into Active Simultaneous Localization and Mapping (A-SLAM), enabling autonomous mapping of unstructured environments while continuously optimizing the underlying map representation.

My SuperUROP project will give me the chance to contribute towards more capable and robust robotic systems. I look forward to developing and testing my work, and pushing towards more useful robots for the future.