DANAE: a denoising autoencoder for underwater attitude estimation
Paolo Russo, Fabiana Di Ciaccio, Salvatore Troisi
TL;DR
Underwater robot attitude estimation faces severe noise and calibration challenges that hinder KF-based orientation tracking. The authors propose DANAE, a filter-agnostic denoising autoencoder that maps KF-derived Euler angles $$(\phi, \theta, \psi)$$ to ground-truth attitudes, effectively compensating both stochastic and systematic errors. On OxIOD and UCS datasets, DANAE delivers substantial RMSE reductions (approximately $55$–$63\%$) and smoother angle trajectories, demonstrating robust performance across different noise regimes. This approach reduces the reliance on meticulous KF tuning and shows potential for real-time underwater navigation when integrated with existing filters like KF, EKF, or UKF. Future work targets online deployments and extending to non-linear filters.
Abstract
One of the main issues for underwater robots navigation is their accurate positioning, which heavily depends on the orientation estimation phase. The systems employed to this scope are affected by different noise typologies, mainly related to the sensors and to the irregular noise of the underwater environment. Filtering algorithms can reduce their effect if opportunely configured, but this process usually requires fine techniques and time. In this paper we propose DANAE, a deep Denoising AutoeNcoder for Attitude Estimation which works on Kalman filter IMU/AHRS data integration with the aim of reducing any kind of noise, independently of its nature. This deep learning-based architecture showed to be robust and reliable, significantly improving the Kalman filter results. Further tests could make this method suitable for real-time applications on navigation tasks.