elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Learning Multiplicative Interactions with Bayesian Neural Networks for Visual-Inertial Odometry

Shinde, Kashmira and Lee, Jongseok and Humt, Matthias and Sezgin, Aydin and Triebel, Rudolph (2020) Learning Multiplicative Interactions with Bayesian Neural Networks for Visual-Inertial Odometry. In: Workshop on AI for Autonomous Driving (AIAD), the 37th International Conference on Machine Learning (ICML). Workshop on AI for Autonomous Driving (AIAD), the 37 th International Conference on Machine Learning (ICML), Vienna, Austria.

[img] PDF
2MB

Abstract

This paper presents an end-to-end multi-modal learning approach for monocular Visual-Inertial Odometry (VIO), which is specifically designed to exploit sensor complementarity in the light of sensor degradation scenarios. The proposed network makes use of a multi-head self-attention mechanism that learns multiplicative interactions between multiple streams of information. Another design feature of our approach is the incorporation of the model uncertainty using scalable Laplace Approximation. We evaluate the performance of the proposed approach by comparing it against the end-to-end state-of-the-art methods on the KITTI dataset and show that it achieves superior performance. Importantly, our work thereby provides an empirical evidence that learning multiplicative interactions can result in a powerful inductive bias for increased robustness to sensor failures.

Item URL in elib:https://elib.dlr.de/135547/
Document Type:Conference or Workshop Item (Other)
Title:Learning Multiplicative Interactions with Bayesian Neural Networks for Visual-Inertial Odometry
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iD
Shinde, KashmiraKashmira.Shinde (at) dlr.deUNSPECIFIED
Lee, JongseokJongseok.Lee (at) dlr.deUNSPECIFIED
Humt, MatthiasDLRUNSPECIFIED
Sezgin, AydinRuhr-Universität BochumUNSPECIFIED
Triebel, RudolphRudolph.Triebel (at) dlr.deUNSPECIFIED
Date:13 July 2020
Journal or Publication Title:Workshop on AI for Autonomous Driving (AIAD), the 37th International Conference on Machine Learning (ICML)
Refereed publication:No
Open Access:Yes
Gold Open Access:No
In SCOPUS:No
In ISI Web of Science:No
Status:Published
Keywords:Multimodal learning, Autonomous Driving, Visual-Inertial Odometry, Robot Perception, Machine Learning, Deep Learning
Event Title:Workshop on AI for Autonomous Driving (AIAD), the 37 th International Conference on Machine Learning (ICML)
Event Location:Vienna, Austria
Event Type:Workshop
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Space System Technology
DLR - Research area:Raumfahrt
DLR - Program:R SY - Space System Technology
DLR - Research theme (Project):R - Vorhaben Intelligente Mobilität (old), Vorhaben Intelligente Mobilität (old)
Location: Oberpfaffenhofen
Institutes and Institutions:Institute of Robotics and Mechatronics (since 2013)
Institute of Robotics and Mechatronics (since 2013) > Perception and Cognition
Deposited By: Lee, Jongseok
Deposited On:21 Jul 2020 09:46
Last Modified:21 Jul 2020 09:46

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.