Google Scholar    Github

I am a final year Ph.D. student at The Robotics Institute at Carnegie Mellon University advised by Michael Kaess. Currently, my research is supported by Facebook AI Research, where I am a Visiting Researcher. I am also a recipient of the CMU Presidential Fellowship (2018).

I’m interested in efficient inference from complex, partially observable sensor data sequences. I approach this problem by leveraging machine learning to extract salient information and sparse optimization to efficiently fuse such information. Currently, I work on learning deep energy-based models in sparse factor graphs for tactile image sequences. My long-term goal is to develop increasingly better computational models for perception that enable rich, human-like explanations of the world.

I have applied my work to diverse real-world robot applications with varying sensor modalities such as tactile images, underwater sonar data, and agricultural images.


Recent News

Aug '21 Check out the arXiV preprint of our recent work on learning energy-based models in factor graph optimization! Links: Paper+Code+Video.
Jul '21 Selected to the 2021 cohort of RSS Pioneers! Links: poster, statement.
May '21 Excited to present our paper on learning tactile models for factor graph-based estimation at ICRA'21. Links: Paper+Code+Video.
Dec '20 Successfully completed my thesis proposal! Talk available here.
Dec '20 Excited to present our work on learning tactile observation models in factor graphs as a contributed talk at the WiML workshop, NeurIPS'20.
Aug '20 Spent a lovely summer at Facebook AI research on tracking object states using tactile image sensors during robot manipulation.
Jun '20 Excited to present our work on incremental constrained smoothing (ICS) in factor graphs at ICRA'20. Check out our paper and talk!
Nov '19 Check out our work on online and consistent occupancy mapping with factor graphs at IROS'19 paper, IROS'18 paper.