RIO: Rotation-equivariance supervised learning of robust inertial odometry
Xiya Cao, Caifa Zhou, Dandan Zeng, Yongliang Wang
Abstract
This paper introduces rotation-equivariance as a self-supervisor to train inertial odometry models. We demonstrate that the self-supervised scheme provides a powerful supervisory signal at training phase as well as at inference stage. It reduces the reliance on massive amounts of labeled data for training a robust model and makes it possible to update the model using various unlabeled data. Further, we propose adaptive Test-Time Training (TTT) based on uncertainty estimations in order to enhance the generalizability of the inertial odometry to various unseen data. We show in experiments that the Rotation-equivariance-supervised Inertial Odometry (RIO) trained with 30% data achieves on par performance with a model trained with the whole dataset. Adaptive TTT improves models' performance in all cases and makes more than 25% improvements under several scenarios. We release our code and dataset at this website.