M2CURL: Sample-Efficient Multimodal Reinforcement Learning via Self-Supervised Representation Learning for Robotic Manipulation

no code implementations • 30 Jan 2024 • Fotios Lygerakis, Vedant Dave, Elmar Rueckert

One of the most critical aspects of multimodal Reinforcement Learning (RL) is the effective integration of different observation modalities.

reinforcement-learning Reinforcement Learning (RL) +3

Multimodal Visual-Tactile Representation Learning through Self-Supervised Contrastive Pre-Training

no code implementations • 22 Jan 2024 • Vedant Dave, Fotios Lygerakis, Elmar Rueckert

In evaluating our methodology, we focus on two distinct tasks: material classification and grasping success prediction.

Contrastive Learning Material Classification +1

Orientation Probabilistic Movement Primitives on Riemannian Manifolds

no code implementations • 28 Oct 2021 • Leonel Rozo, Vedant Dave

Learning complex robot motions necessarily demands to have models that are able to encode and retrieve full-pose trajectories when tasks are defined in operational spaces.