VANP and TAL, two models that use SSL to understand the surrounding in indoor/outdoor environments and vertically challenging terrains are on arXiv.
CAHSOR: Competence-Aware High-Speed Off-Road Ground Navigation that uses SSL to augment vision space with IMU data is on arXiv.
Verti-wheelers was accepted at ICRA 2024.
MuSoHu: A Large-Scale, Multi-Modal, Social Human Navigation Dataset was accepted at IROS 2023.
Published 'Exploring Reflective Limitation of Behavior Cloning in Autonomous Vehicles' at 2021 IEEE International Conference on Data Mining (ICDM).
Published 'Toward Human-Like Social Robot Navigation: A Large-Scale, Multi-Modal, Social Human Navigation Dataset' at 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).
Published 'CAHSOR: Competence-Aware High-Speed Off-Road Ground Navigation in SE (3)' as an arXiv preprint.
Published 'VANP: Learning Where to See for Navigation with Self-Supervised Vision-Action Pre-Training' as an arXiv preprint.
Research Experience
Member of the RobotiXX lab, working on mobile robot perception and autonomous navigation.
Education
Ph.D. Student in Computer Science, George Mason University (in progress)
Background
A second year Ph.D. student in the Computer Science Department at George Mason University, focusing on helping mobile robots become more aware of their surroundings and navigate autonomously with minimal human supervision. He approaches this by designing self-supervised algorithms that unify multiple data modalities.