Journal
IEEE TRANSACTIONS ON ROBOTICS
Volume 36, Issue 6, Pages 1738-1757Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TRO.2020.3001674
Keywords
Uncertainty; Estimation; Measurement uncertainty; Computational modeling; Training; Computer architecture; Feature extraction; Computer vision for transportation; deep learning in robotics and automation; localization; visual learning
Categories
Funding
- University of Perugia [RICBA17MRF]
Ask authors/readers for more resources
Over the past few years, we have witnessed a considerable diffusion of data-driven visual odometry (VO) approaches as viable alternatives to standard geometric-based strategies. Their success is mainly related to the improved robustness to image nonideal conditions (e.g., blur, high or low contrast, texture-poor scenarios). However, most of the data-driven State-of-the-Art (SotA) approaches do not provide any kind of information about the uncertainty of their estimates, which is crucial to effectively integrate them into robotic navigation systems. Inspired by this considerations, we propose uncertainty-aware VO (UA-VO), a novel deep neural network (DNN) architecture that computes relative pose predictions by processing sequence of images and, at the same time, provides uncertainty measures about those estimations. The confidence measure computed by UA-VO considers both epistemic and aleatoric uncertainties and accounts for heteroscedasticity, i.e., it is sample-dependent. We assess the benefits of UA-VO with different typology of experiments on three publicly available datasets and on a brand new set of sequences, we gathered to extend the evaluation.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available