Projects

Learning with Less Labeling (LwLL)

We propose a novel algorithm for semi-supervised classification that achieves state-of-the-art performance on standard benchmarks and outperform previous works on transfer setting by a large margin.

Trust in Multi-Party Human-Robot Interaction

We designed and evaluated a novel framework for robot mediation of a support group

Telepresence Robot for K-12 Remote Education

We developed and evaluated various control methods and interfaces for mobile remote presence robots (we used [Ohmni](https://ohmnilabs.com/products/ohmnirobot/) robot) for remote K-12 education

Resource Distribution in Human-Robot Teams

Our work provides an algorithm that takes into account the social construct of human fairness and optimization through a Multi Armed Bandit variant algorithm

Decentralized Federated Multi-Task Learning and System Design

We designed a decentralized multi-task learning framework and a novel optimization algorithm to collaboratively train models over distributed devices by only sharing their gradient periodically

Infant-Robot Interaction as an Early Intervention Strategy

Our goal is to develop a socially assistive, non-contact, infant-robot interaction system to provide contingent positive feedback to increase exploration and expand early movement practice