Shuli Lv
Papers
2
Total Citations
20
H-Index
2
About
Shuli Lv is pioneering the frontier of swarm robotics, tackling the grand challenge of coordinating large-scale robot teams through complex, obstacle-dense environments. Her research masterfully fuses homotopic path planning, iterative learning control, and mean-field theory to unlock unprecedented efficiency and safety for multi-agent systems. Lv’s most impactful contribution is the "Tube RRT*" algorithm (2025, 15 citations), which introduces a novel homotopic trajectory planning framework that enables swarms to navigate through large-scale obstacles by considering topological path classes—a critical advancement over traditional methods that fail in cluttered spaces. Complementing this, her work on "Mean-Field Based Time-Optimal Spatial Iterative Learning Within a Virtual Tube" (2024, 5 citations) offers a groundbreaking approach that uses mean-field feedback to iteratively refine swarm trajectories, optimizing travel time while ensuring collision avoidance. By treating the swarm as a density field rather than individual agents, Lv achieves scalable, time-optimal solutions. Her work is rapidly gaining recognition for bridging theoretical control theory with practical swarm deployment, promising transformative applications in search-and-rescue, autonomous logistics, and environmental monitoring.
Research Focus
Key Achievements
Top Papers
- 1
- 2