ORCID Identifier(s)

https://orcid.org/0000-0003-3793-8492

Graduation Semester and Year

Summer 2025

Language

English

Document Type

Dissertation

Degree Name

Doctor of Philosophy in Computer Science

Department

Computer Science and Engineering

First Advisor

Manfred Huber

Second Advisor

Farhad Kamangar

Third Advisor

David Levine

Fourth Advisor

William Beksi

Abstract

Service robots are migrating from tightly controlled factory lines into offices, hospitals, and homes, where they must perceive, remember, and act amid people, clutter, and perpetual change. Humans solve this daily by forming compact, task-relevant “cognitive maps”: we sample just enough sensory detail to guide the moment, stitch those snapshots into a sparse topological scaffold, and continuously refine it as we move. Guided by that insight, this dissertation proposes a biologically inspired mapping framework that turns partial RGB-D observations into a hybrid temporal-spatial memory—locally metric for centimeter-scale navigation yet globally topological for room-to-building navigation. The system first distills raw depth images into salience-weighted key-frames and learned point-feature fields, echoing bottom-up attention in human vision. These frames are then woven into a two-layer map that mirrors hippocampal place- and grid-cell organization: a symbolic graph for long-range planning overlaid with either a Point-Based Neural Field or fine-grained 3-D Gaussian primitives for high precision in navigation. Coupled with lightweight visual SLAM, the map supports real-time loop closure, semantic landmarking, and obstacle-aware path planning on resource-constrained hardware. As an attempt to translate principles of human spatial cognition into algorithms that run on today’s embedded processors, this work closes the gap between partial visual perception and actionable temporary spatial memory, bringing service robots a step closer to seamless assistance wherever people live and work.

Keywords

Robotics, 3D Perception, Mapping, Navigation

Disciplines

Controls and Control Theory | Robotics

License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.