Yingqi Deng
Papers
1
Total Citations
7
H-Index
1
About
Yingqi Deng is a rising researcher in robotics and autonomous navigation, with a focus on developing intelligent, map-free navigation systems for mobile robots. Their key research areas include spatial-temporal representation learning, bird’s-eye view (BEV) perception, and contrastive learning for decision-making in unstructured environments. Deng’s most notable contribution is the introduction of BEVNav, a novel navigation framework that leverages BEV representations of point cloud data combined with spatial-temporal contrastive learning to enable goal-driven navigation without pre-existing maps. This work, published in 2024 and already garnering 7 citations, addresses a critical challenge in robotics: creating robust state representations for reliable decision-making in dynamic, unknown settings. By bridging perception and planning through learned BEV features, Deng’s approach enhances a robot’s ability to understand its surroundings and navigate efficiently. Their work is particularly impactful for applications in autonomous driving, search-and-rescue, and exploration, where traditional mapping is impractical. As an emerging voice in the field, Deng’s research promises to advance the frontier of intelligent, adaptive robotics.
Research Focus
Key Achievements
Top Papers
- 1