Robert Exley

I am an undergraduate student at the University of Pittsburgh.

My research interests lie in 3D/4D vision, generative world models, and embodied AI. I aim to develop spatially intelligent systems that perceive, reconstruct, and reason about the physical world.

I have had the honor of working with Prof. Sebastian Scherer at the AirLab and Prof. Jaesik Park at the VGI Lab .

news

Jun 04, 2026	Our work AmodalBox is accepted to CoRL 2026!
Aug 25, 2025	I started my exchange at Seoul National University

selected publications

AmodalBox: Automated 3D Bounding Box Annotation under Partial Visibility

In-Jae Lee, Namtae Kim, Robert Exley, and 2 more authors

Proceedings of the The Conference on Robot Learning (CoRL), 2026

Bib

@article{Lee_AmodalBox_CoRL_2026,
  title = {AmodalBox: Automated 3D Bounding Box Annotation under Partial Visibility},
  author = {Lee, In-Jae and Kim, Namtae and Exley, Robert and Ryu, Kwonyoung and Park, Jaesik},
  journal = {Proceedings of the The Conference on Robot Learning (CoRL)},
  year = {2026},
}

BETTY Dataset: A Multi-modal Dataset for Full-Stack Autonomy

Micah Nye, Ayoub Raji, Andrew Saba, and 9 more authors

IEEE International Conference on Robotics and Automation (ICRA), 2025

arXiv Bib Website

@article{nye2025bettydatasetmultimodaldataset,
  title = {BETTY Dataset: A Multi-modal Dataset for Full-Stack Autonomy},
  author = {Nye, Micah and Raji, Ayoub and Saba, Andrew and Erlich, Eidan and Exley, Robert and Goyal, Aragya and Matros, Alexander and Misra, Ritesh and Sivaprakasam, Matthew and Bertogna, Marko and Ramanan, Deva and Scherer, Sebastian},
  journal = {IEEE International Conference on Robotics and Automation (ICRA)},
  year = {2025},
  eprint = {2505.07266},
  archiveprefix = {arXiv},
  primaryclass = {cs.CV},
}