Abstract
Underwater Ultra-Short Baseline (USBL) positioning systems suffer from significant estimation errors due to complex noise characteristics. Our analysis indicates that these errors manifest distinct skewed and heavy-tailed statistical characteristics, primarily attributed to system biases, time delays, and multipath effects. To effectively mitigate these issues, we propose a novel Kalman filter approach utilizing a skew-t distribution (SKF). The SKF employs a hierarchical variational Bayesian approach to resolve linearization challenges caused by distribution asymmetry, using a structured likelihood representation of measurement errors. Simulations and field tests demonstrated that the SKF method improved accuracy by more than 56% in the USBL positioning system.
Funding Information
  • National Natural Science Foundation of China (62073264)
  • National Natural Science Foundation of China (62203358)
  • National Natural Science Foundation of China (52372434)