Kehlani Fay

Hello! My research is in robot learning, studying co-design for embodied intelligence. Embodiement informs both cognition and behavior - so I am interested in understanding what design attributes inform intelligence.

Academically, I am fortunate to have worked with Professor Xiaolong Wang and Professor Michael Tolley . Likewise, I have been fortunate to work with Professor Hao Su and Professor Deepak Pathak.

I am an NSF GRFP fellow.

Publications

Cross-embodied Co-design for Dexterous Hands

Kehlani Fay, Darin Anthony Djapri, Anya Zorin, James Clinton, Ali El Lahib, Hao Su, Michael T. Tolley, Sha Yi, Xiaolong Wang

International Conference on Learning Representations (ICLR), 2026

project page arXiv

Catch It All!: Generalizable Dynamic Catching with a Dexterous Hand

Kehlani Fay*, Arth Shukla*, Patrick Liu, Darin Djapri, Alexiy Buynitsky, Nicklas Hansen

Pre-Arxiv, Conference Submission

pre-release project page pre-Arxiv

Towards Embodiment Scaling Laws in Robot Locomotion

Bo Ai, Liu Dai, Nico Bohlinger, Dichen Li, Tongzhou Mu, Zhanxin Wu, K. Fay, Henrik I. Christensen, Jan Peters, Hao Su

Conference on Robot Learning (CoRL), 2025

project page arXiv

Multi-AUV Marine Life Tracking with Single Hydrophone Payloads via a Hidden Markov Model Equipped Particle Filter

Christopher Herrera, Kehlani Fay, Christopher Clark, Alberto Soto, Christopher G Lowe, Mario Espinoza

paper

Multi-Robot Expansive Planning and Trajectory Evaluation for Tracking and Localization of Marine Life

Kehlani Fay, Michael Giordano, Alberto Soto, Christopher Clark, Emily Spurgeon, James Anderson, & Christopher Lowe

Symposium On Applied Computing, 2023

slides pdf

Works that never fully fermented, but still cool :)

Risk Aware Racing Agents: Learning Adaptive Policies in Competitive Racing Games

Kehlani Fay & Victor Shia

RSS Workshop