Abstract: Existing compression methods typically focus on the removal of signal-level redundancies, while the potential and versatility of decomposing visual data into compact conceptual components ...

Abstract: Disentangled representation learning aims at obtaining an independent latent representation without supervisory signals. However, the independence of a representation does not guarantee ...

This research project investigates whether Inverse Reinforcement Learning (IRL) based intention recognition algorithms can improve human-robot cooperation in assistive systems. Inspired by how ...