Pengying Wu
Papers
2
Total Citations
11
H-Index
2
About
Pengying Wu is a rising star in embodied AI and swarm robotics, whose work bridges large language models and multi-agent systems to solve real-world navigation challenges. Her seminal paper, “VoroNav: Voronoi-based Zero-shot Object Navigation with Large Language Model” (2024, 8 citations), introduces a novel semantic exploration framework that leverages Voronoi diagrams and LLMs to enable household robots to navigate unfamiliar environments and locate novel objects without prior training—a breakthrough for zero-shot generalization in robotics. Building on this, her 2025 work “SwarmDiff: Swarm Robotic Trajectory Planning in Cluttered Environments via Diffusion Transformer” (3 citations) tackles the critical issues of computational efficiency and safety in dense obstacle fields, proposing a hierarchical generative framework that models swarm macro-behavior with diffusion transformers. Wu’s contributions are particularly notable for their practical impact: VoroNav’s zero-shot capability reduces the need for expensive retraining, while SwarmDiff’s scalable approach promises safer, more efficient coordination for drone swarms and warehouse robots. Her research, already cited in top venues, positions her as a key innovator at the intersection of semantic reasoning and multi-robot planning.
Research Focus
Key Achievements
Top Papers
- 1
- 2