He Jiang
Papers
3
Total Citations
18
H-Index
2
About
He Jiang is an emerging researcher specializing in **Multi-Agent Path Finding (MAPF)** and scalable robot coordination, with a particular focus on lifelong planning systems designed for real-world deployment. His work addresses one of robotics' most demanding challenges: coordinating large numbers of autonomous agents in dynamic environments where goals are continuously reassigned rather than fixed. Jiang's most significant contributions center on Lifelong Multi-Agent Path Finding (LMAPF), where he has pioneered both competition-winning classical approaches and cutting-edge learning-based methods. His team's winning entry in the prestigious **2023 League of Robot Runners LMAPF competition** — detailed in his most-cited paper with 13 citations — demonstrated exceptional scalability under realistic constraints. Building on this foundation, his 2025 work on imitation learning pushes the boundary further, achieving coordination for up to **ten thousand robots** simultaneously through data-driven, reactive planning strategies. What distinguishes Jiang's research is its dual commitment to theoretical rigor and practical applicability, consistently identifying open research challenges that bridge competition benchmarks and real-world warehouse or logistics scenarios. Though early in his career, his work has already attracted meaningful attention from the robotics and AI planning communities, positioning him as a promising voice in large-scale multi-agent systems research.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3