ResAlignNet aligns INS and DVL sensors to 0.8 degrees accuracy in 25 seconds using deep learning on synthetic-to-real data, reducing convergence time by 65% without prescribed motions or external positioning.
A least squares estimate of satellite attitude
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Proposes SIME framework with AM and AM-SDR solvers for 3D rotation search and rigid point-set registration, claiming lower fitting residuals than MC-based methods on high-outlier data.
citing papers explorer
-
ResAlignNet: A Data-Driven Approach for INS/DVL Alignment
ResAlignNet aligns INS and DVL sensors to 0.8 degrees accuracy in 25 seconds using deep learning on synthetic-to-real data, reducing convergence time by 65% without prescribed motions or external positioning.
-
A Robust 3D Registration Method via Simultaneous Inlier Identification and Model Estimation
Proposes SIME framework with AM and AM-SDR solvers for 3D rotation search and rigid point-set registration, claiming lower fitting residuals than MC-based methods on high-outlier data.