Future Works

Hongmin Wu

I am a PhD. Candidate in robotics. The primary goal of my research is to enable personal robots to be deployed in the home and workplace with minimal intervention by robotics experts. With this in mind, we equip robots with a set of abilities that allows them to assess the quality of sensory data, internal modals, used the Bayesian Nonparametric methods, LSTM, Seq2Seq, and Variational Autoencoder for learning dynamical models for multimodal time series with complex and uncertain behavior patterns. Thus, my work draws roughly equally from both machine learning and robotics, including learning from demonstration, movement representation, robot introspection (anomaly detection, classification, recovery), human-robot interaction, and deep learning.

Post-doc

Variational Autoencoder inference for HDPHMM
Project proposal about Multimodal Anomaly Detection
A team for long-term autonomous robot manipulation task
Introspective System
Improving our visual system for object pose estimation and graspping configuration optimization

Post-doc

Introspective System