Papers
2
Total Citations
70
H-Index
2
About
Keji He is a rising researcher in embodied artificial intelligence, with a primary focus on vision-language navigation (VLN) and multi-agent robotic systems. His most impactful contribution is the development of **ETPNav**, a novel framework for evolving topological planning that enables agents to follow natural language instructions while navigating continuous environments. This work, published in 2024, has already garnered **64 citations**, reflecting its significance in advancing autonomous navigation for applications in search-and-rescue and human-robot interaction. Earlier in his career, He contributed to multi-robot coordination through his work on **RoboCup 3D soccer robots**, where he applied Delaunay triangulation networks to optimize team formations and collaborative strategies. Though this earlier paper has a modest citation count of 6, it demonstrates his foundational interest in spatial reasoning and cooperative control. He’s research bridges the gap between high-level linguistic understanding and low-level motion planning, tackling key challenges in embodied AI. His work on ETPNav, in particular, stands out for its practical approach to continuous environment navigation, making him a notable voice in the VLN community.
Research Focus
Key Achievements
Top Papers
- 1
- 2