Papers
1
Total Citations
2
H-Index
1
About
Rina Wu is a leading researcher in robotic dexterous manipulation, with a primary focus on visuo-tactile fusion and multi-agent deep reinforcement learning. Her most-cited work, "Multi-fingered Hand Grasps with Visuo-Tactile Fusion via Multi-Agent Deep Reinforcement Learning," introduces a novel framework that synergizes visual and tactile feedback to control high-degree-of-freedom robotic hands—a breakthrough in overcoming the complexity of contact-rich grasping. By decomposing the high-dimensional action space into manageable agent-based policies, Wu’s approach enables more stable and adaptive hand-object interactions, directly advancing the field of autonomous manipulation. Though early in its citation trajectory, this work has already garnered attention for its innovative integration of sensory modalities and reinforcement learning. Wu’s contributions are pivotal for applications in assistive robotics, manufacturing, and prosthetics, where precise, human-like grasping is essential. Her research not only pushes the boundaries of robotic dexterity but also provides a scalable framework for future multi-sensory control systems, marking her as a rising star in robotics and artificial intelligence.
Research Focus
Key Achievements
Top Papers
- 1