Shenghai Yuan

Papers

Total Citations

H-Index

About

Shenghai Yuan is at the forefront of multi-agent robotic systems, specializing in Simultaneous Localization and Mapping (SLAM) and autonomous exploration. His research addresses critical challenges in enabling teams of robots to collaboratively perceive, navigate, and map complex environments. Yuan’s most cited work, "MNE-SLAM: Multi-Agent Neural SLAM for Mobile Robots" (2025, 18 citations), pioneers the extension of neural implicit scene representations—a cutting-edge approach in dense visual SLAM—from single-robot to multi-robot scenarios. This breakthrough overcomes the limitations of single-agent systems in large indoor spaces and long sequences, while also surpassing traditional multi-agent SLAM frameworks. In another key contribution, "Multi-Robot Active Graph Exploration with Reduced Pose-SLAM Uncertainty via Submodular Optimization" (2024, 8 citations), Yuan tackles the dual challenge of efficient environment coverage and reliable pose estimation. By formulating the problem as a submodular optimization, his work enables robots to intelligently balance exploration with maintaining high-quality SLAM, a critical step toward robust, real-world multi-robot operations. Yuan’s research is shaping the future of autonomous robotics, with direct implications for search-and-rescue, warehouse automation, and large-scale environmental monitoring.