Wenbin Song
Papers
3
Total Citations
30
H-Index
2
About
Wenbin Song is a rising researcher at the intersection of robotics, human-robot interaction (HRI), and embodied AI, with a focus on creating intelligent, socially-aware autonomous systems. His work is distinguished by pioneering the integration of large language models (LLMs) with multimodal inputs—such as language and sketching—to enable intuitive, multitask robot navigation. His 2024 paper on an LLM-driven interactive framework, which has already garnered 23 citations, addresses a critical gap in HRI by allowing robots to fluidly interpret and execute complex commands like point-to-point navigation, human-following, and guiding in dynamic environments. Beyond terrestrial robotics, Song has made notable contributions to bio-inspired underwater robotics, developing novel learning-based control policies for fish-like robots to navigate complex fluid flows, enhancing their maneuverability and efficiency. His most recent work extends into digital twin systems, creating fluid-interactive virtual agents with local-domain control for realistic simulation and testing. By bridging natural language, multimodal communication, and adaptive control across air, land, and sea domains, Wenbin Song is shaping the future of versatile, intelligent robots that can collaborate seamlessly with humans in the real world.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3