Kai Dai
Papers
2
Total Citations
45
H-Index
2
About
Kai Dai is a leading researcher in autonomous vehicle localization, with a primary focus on visual-inertial odometry (VIO) for intelligent and connected vehicles. His work addresses a critical challenge in this field: the loss of observability and increased pose estimation errors that occur when ground vehicles undergo degenerate, non-holonomic motions. Dai’s major contribution is the development of tightly-coupled fusion frameworks that integrate Ackermann steering constraints into standard VIO systems. His seminal paper, "ACK-MSCKF: Tightly-Coupled Ackermann Multi-State Constraint Kalman Filter for Autonomous Vehicle Localization" (2019, 39 citations), introduced a novel approach to correct unobservable directions by fusing Ackermann error state measurements, significantly improving localization accuracy. He further advanced this concept in "Consistent Monocular Ackermann Visual–Inertial Odometry for Intelligent and Connected Vehicle Localization" (2020, 6 citations), where he addressed the scale observability problem under constant-velocity assumptions. By bridging the gap between theoretical observability analysis and practical deployment, Dai’s work has provided a robust foundation for reliable, low-cost localization in urban driving scenarios. His research is essential reading for engineers and researchers working on sensor fusion and autonomous navigation.
Research Focus
Key Achievements
Top Papers
- 1
- 2