Papers
2
Total Citations
36
H-Index
2
About
Yijie Zeng is a researcher advancing the frontiers of embodied AI and autonomous robotics, with a focus on integrating perception, reasoning, and decision-making. Their work centers on multimodal information fusion and visual-language alignment, enabling robots to interpret complex environments and execute goal-driven tasks. Zeng’s highly cited 2018 paper, “Knowledge-based multimodal information fusion for role recognition and situation assessment by using mobile robot” (30 citations), laid foundational methods for combining sensory data with contextual knowledge to improve robotic situational awareness. More recently, their 2024 work “VLAI: Exploration and Exploitation based on Visual-Language Aligned Information for Robotic Object Goal Navigation” (6 citations) introduces a novel framework that leverages aligned visual and language representations to balance exploration and exploitation, significantly enhancing a robot’s ability to locate objects in unseen spaces. This contribution is particularly impactful for real-world applications like search-and-rescue and domestic assistance. By bridging vision, language, and action, Zeng is helping to shape the next generation of intelligent, autonomous systems that understand and navigate the world as humans do.
Research Focus
Key Achievements
Top Papers
- 1
- 2