Embedded Files
Research topic:
Research topic:
Informative Exploratory Motions for System Identification through Reinforcement Learning
Tool-use skills learning through few-shot human demonstrations with proximity and tactile sensing
Few-Shot Learning of Force-Based Motions From Demonstration Through Pre-training of Haptic Representation
Structured motion generation with predictive learning: Proposing subgoal for long-horizon manipulation
Projects
Projects
Poke and Strike: Learning Task-Informed Exploration Policies
Tool-use skills learning through few-shot human demonstrations with proximity and tactile sensing
Keywords: manipulation, Learning from Demonstration, tactile sensing, proximity sensing, sensorimotor control, deep learning, sim2real
IEEE Robotics and Automation Letters (RA-L) 2025.
Marina. Y. Aoyama, Sethu Vijayakumar and Tetsuya Narita
Work conducted during an internship at Sony Group Corporation.
Few-Shot Learning of Force-Based Motions From Demonstration Through Pre-training of Haptic Representation
Keywords: manipulation, Learning from Demonstration, force, sensorimotor control, deep learning, unsupervised learning, self-supervised learning, generative model, sim2real
IEEE International Conference on Robotics & Automation (ICRA) 2024.
Marina Y. Aoyama, Joao Moura, Namiko Saito and Sethu Vijayakumar
[arxiv][paper][video][presentation][poster]
Structured motion generation with predictive learning: Proposing subgoal for long-horizon manipulation
Page updated
Google Sites
Report abuse