Presents a novel architecture for robot learning of haptic interaction, achieving robust object class estimation and enhancing haptic interaction efficiency.
Explores training robots through reinforcement learning and learning from demonstration, highlighting challenges in human-robot interaction and data collection.
Explores Bayesian disturbance injection for robust imitation in robot learning, demonstrating its effectiveness in reducing error compounding and achieving high task achievement.
Delves into self-reconfigurable modular robots, discussing advantages, design concepts, planning strategies, and challenges in motion planning and search algorithms.
Explores advancements in robot learning for autonomy at scale, covering deep learning challenges, efficient architecture, benchmarking results, and societal implications.
Explores challenges and opportunities in vision-based robotic perception, covering topics like SLAM, place recognition, event cameras, and collaborative visual intelligence.
