5 papers
Tactile Modality Fusion for Vision-Language-Action Models
Charlotte Morissette, Amin Abyaneh, Wei-Di Chang +5
We propose TacFiLM, a lightweight modality-fusion approach that integrates visual-tactile signals into vision-language-action (VLA) models. While advances in VLAs have introduced r…
Contractive Diffusion Policies: Robust Action Diffusion via Contractive Score-Based Sampling with Differential Equations
Amin Abyaneh, Charlotte Morissette, Mohamad H. Danesh +4
Diffusion policies have emerged as powerful generative models for offline policy learning, whose sampling process can be rigorously characterized by a score function guiding a stoc…
Scalable Aerial GNSS Localization for Marine Robots
Shuo Wen, Edwin Meriaux, Mariana Sosa Guzmán +4
Accurate localization is crucial for water robotics, yet traditional onboard Global Navigation Satellite System (GNSS) approaches are difficult or ineffective due to signal reflect…
A Study of Human-Robot Handover through Human-Human Object Transfer
Charlotte Morissette, Bobak H. Baghi, Francois R. Hogan +1
In this preliminary study, we investigate changes in handover behaviour when transferring hazardous objects with the help of a high-resolution touch sensor. Participants were asked…
Hypernetworks for Zero-shot Transfer in Reinforcement Learning
Sahand Rezaei-Shoshtari, Charlotte Morissette, Francois Robert Hogan +2
In this paper, hypernetworks are trained to generate behaviors across a range of unseen task conditions, via a novel TD-based training objective and data from a set of near-optimal…