Papers
4
Total Citations
19
H-Index
2
About
Xiaokai Mu is a robotics researcher whose work centers on autonomous navigation, underwater rescue robotics, and bio-inspired mechanical design. His research addresses critical challenges in state estimation and environmental perception for unmanned systems operating in complex, dynamic settings. Mu’s most cited paper, “Visual Navigation Features Selection Algorithm Based on Instance Segmentation in Dynamic Environment” (2019, 12 citations), advances ego-motion estimation for autonomous robots and unmanned vehicles by integrating instance segmentation to filter out dynamic obstacles—a key contribution to robust visual odometry. He has also pioneered deep learning-based detection systems for emergency rescue, notably with “Underwater Drowning People Detection Based on Bottleneck Transformer and Feature Pyramid Network” (2022, 3 citations), enabling underwater robots to autonomously identify victims in murky conditions. More recently, Mu introduced a “Geometric Extended Kalman Filter With Dual Robust Kernels for Integrated Navigation” (2025, 2 citations), a novel framework that significantly improves attitude and position estimation accuracy under sensor noise. His work on the “Amphibious Crab-Like Robot” (2024, 2 citations) demonstrates his versatility in mechanical design, optimizing leg kinematics for nearshore and seabed operations. With a growing citation record, Mu’s contributions are shaping the future of resilient, intelligent autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4