Wenguan Wang
Papers
5
Total Citations
122
H-Index
5
About
Wenguan Wang is a leading researcher in embodied AI, with a primary focus on vision-language navigation (VLN) and audio-visual navigation. His work centers on creating intelligent agents that can perceive, reason, and act in complex, continuous environments by integrating natural language understanding with spatial awareness. Wang’s major contributions include pioneering the development of language-capable navigators that go beyond simple instruction-following. His notable work, **LANA**, introduces a dual-capability agent that can both follow navigation instructions and generate them, effectively enabling human-robot dialogue. This shift from "dumb" wayfinding to interactive navigation represents a significant leap in the field. In **ETPNav**, he addresses the challenge of long-horizon planning in continuous environments by evolving topological maps, a work that has rapidly garnered 64 citations since 2024. Additionally, his research on **ORAN** advances audio-visual navigation by enabling agents to locate sound sources in unseen 3D spaces through cross-task skill transfer. With a growing citation impact and a focus on bridging perception, language, and action, Wang is shaping the future of autonomous agents for applications in search and rescue, service robotics, and human-robot interaction.
Research Focus
Key Achievements
Top Papers
- 1
- 2LANA: A Language-Capable Navigator for Instruction Following and Generation33 citations · 2023
- 3
- 4
- 5