Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

RIO: Rotation-equivariance supervised learning of robust inertial odometry

About

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 database. Adaptive TTT improves models performance in all cases and makes more than 25% improvements under several scenarios.

Caifa Zhou, Xiya Cao, Dandan Zeng, Yongliang Wang• 2021

Related benchmarks

TaskDatasetResultRank
Inertial OdometryRONIN (test)
ATE (m)5.02
13
Inertial OdometryOXIOD (test)
ATE (m)2.92
5
Inertial OdometryRIDI (test)
ATE (m)1.03
5
Inertial OdometryIPS (test)
Absolute Trajectory Error (m)1.55
5
Showing 4 of 4 rows

Other info

Follow for update