High-precision optoelectronic fusion for rail transit applications
This paper proposes a real-time fusion algorithm of Ultra-Wideband (UWB) and Inertial Measurement Unit (IMU) information based on the Error-State Kalman Filter (ESKF) algorithm, aiming to achieve high-precision train positioning throughout the entire railway, particularly in tunnel. Moreover, accurate localization paves the way for a variety of advanced key applications such as Automated Train Operation (ATO), making it a prereq npoint posi-tioning at all times. Three core improvements were integrated: 1) AVCStem module with variable convolution kernels to dynamically adapt to defects of different shapes and scales; 2) ADSPPF module using multi-scale pooling and multi-branch attention mechanisms to preserve fine-grained features across scales; 3) MSF.
Read More