e-obs Stories & Publications
Discover a World of Wildlife Science
With over two decades of unwavering commitment to serving the needs of tagged animals and our valued customers, we’ve forged deep connections in the world of wildlife research. Our relentless passion drives us to continually elevate our products, expanding our portfolio to benefit you.
Proven Impact
Our products have played a pivotal role in countless studies, spanning a diverse array of remarkable creatures, from coconut crabs (Birgus latro) to majestic red kites (Milvus milvus) and agile cheetahs (Acinonyx jubatus). The e-obs community, fueled by our technology, consistently pushes the boundaries of wildlife science, resulting in a wealth of publications that testify to the excellence of our materials and the exceptional work of our users.
Brossard, Martin; Barrau, Axel; Bonnabel, Silvère
AI-IMU Dead-Reckoning Journal Article
In: IEEE Transactions on Intelligent Vehicles, vol. 5, no. 4, pp. 585–595, 2020, ISSN: 2379-8904.
Abstract | Links | BibTeX | Tags: dead reckoning, deep learning, Image sensors, inertial measurement unit (IMU), inertial navigation, invariant extended Kalman filter, Kalman filters, KITTI dataset, Localization, Sensors
@article{brossard_ai-imu_2020,
title = {AI-IMU Dead-Reckoning},
author = {Martin Brossard and Axel Barrau and Silv\`{e}re Bonnabel},
url = {https://ieeexplore.ieee.org/abstract/document/9035481/authors},
doi = {10.1109/TIV.2020.2980758},
issn = {2379-8904},
year = {2020},
date = {2020-12-01},
urldate = {2026-03-21},
journal = {IEEE Transactions on Intelligent Vehicles},
volume = {5},
number = {4},
pages = {585\textendash595},
abstract = {In this paper, we propose a novel accurate method for dead-reckoning of wheeled vehicles based only on an Inertial Measurement Unit (IMU). In the context of intelligent vehicles, robust and accurate dead-reckoning based on the IMU may prove useful to correlate feeds from imaging sensors, to safely navigate through obstructions, or for safe emergency stops in the extreme case of exteroceptive sensors failure. The key components of the method are the Kalman filter and the use of deep neural networks to dynamically adapt the noise parameters of the filter. The method is tested on the KITTI odometry dataset, and our dead-reckoning inertial method based only on the IMU accurately estimates 3D position, velocity, orientation of the vehicle and self-calibrates the IMU biases. We achieve on average a 1.10% translational error and the algorithm competes with top-ranked methods which, by contrast, use LiDAR or stereo vision.},
keywords = {dead reckoning, deep learning, Image sensors, inertial measurement unit (IMU), inertial navigation, invariant extended Kalman filter, Kalman filters, KITTI dataset, Localization, Sensors},
pubstate = {published},
tppubtype = {article}
}