denoise-imu-gyro - GitLite

KO | EN

gitlite — search

#javascript #python #llm #golang #android #machine-learning #rust #deep-learning #java #awesome-list #security #openai #mcp #open-source

denoise-imu-gyro

(★ 417)

Convolutional Neural Networks for Denoising Gyroscopes of Low-Cost IMUs

파일 탐색기

최종 버전 다운로드 (.zip)

- boxplot.jpg
- methode.jpg
- roe.jpg
- rpy.jpg
- dataset.py
- learning.py
- lie_algebra.py
- losses.py
- networks.py
- utils.py
.gitignore
LICENCE
main_EUROC.py
main_TUMVI.py
README.md
requirements.txt

# 설치 가이드

1. 코드 내려받기

git clone https://github.com/mbrossar/denoise-imu-gyro

깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.

cd denoise-imu-gyro

방금 내려받은 프로젝트 폴더 안으로 이동합니다.

2. 공식 설치 스크립트

쉬움 추천

사전 준비물

Python 3 pip 명령어를 쓰려면 Python이 필요합니다.

pip install --pre torch -f https://download.pytorch.org/whl/nightly/cu101/torch_nightly.html

PyPI에 배포된 패키지를 바로 설치합니다. 소스 클론이 필요 없습니다.

✅ 설치 후 새 터미널을 열고, 프로그램의 버전 확인 명령(예: --version)으로 정상 설치됐는지 확인하세요.

이 레포의 README에 적힌 실제 명령어를 그대로 가져왔습니다.

3. Python

쉬움

사전 준비물

Git GitHub에서 프로젝트 코드를 내려받으려면 필요합니다.
Python 3 설치 시 'Add Python to PATH' 옵션을 꼭 체크하세요 (Windows).

pip install --pre torch -f https://download.pytorch.org/whl/nightly/cu101/torch_nightly.html

PyPI에 배포된 패키지를 바로 설치합니다. 소스 클론이 필요 없습니다.

pip install -r denoise-imu-gyro/requirements.txt

requirements.txt 등에 명시된 파이썬 라이브러리를 설치합니다.

✅ 에러 메시지 없이 실행되고 터미널에 안내 문구가 출력되면 정상입니다.

이 레포의 README에 적힌 실제 명령어를 그대로 가져왔습니다.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Denoising IMU Gyroscope with Deep Learning for Open-Loop Attitude Estimation

## Overview [[IEEE paper](https://ieeexplore.ieee.org/document/9119813), [preprint paper](https://hal.archives-ouvertes.fr/hal-02488923v4/document)]

This repo contains a learning method for denoising gyroscopes of Inertial Measurement Units (IMUs) using
ground truth data. In terms of attitude dead-reckoning estimation, the obtained algorithm is able to beat top-ranked
visual-inertial odometry systems [3-5] in terms of attitude estimation
although it only uses signals from a low-cost IMU. The obtained
performances are achieved thanks to a well chosen model, and a
proper loss function for orientation increments. Our approach builds upon a neural network based
on dilated convolutions, without requiring any recurrent neural
network.

## Code
Our implementation is based on Python 3 and [Pytorch](https://pytorch.org/). We
test the code under Ubuntu 16.04, Python 3.5, and Pytorch 1.5. The codebase is licensed under the MIT License.

### Installation & Prerequies
1.  Install the correct version of [Pytorch](http://pytorch.org)
```
pip install --pre torch  -f https://download.pytorch.org/whl/nightly/cu101/torch_nightly.html
```

2.  Clone this repo and create empty directories
```
git clone https://github.com/mbrossar/denoise-imu-gyro.git
mkdir denoise-imu-gyro/data
mkdir denoise-imu-gyro/results
```

3.  Install the following required Python packages, e.g. with the pip command
```
pip install -r denoise-imu-gyro/requirements.txt
```

### Testing

1. Download reformated pickle format of the _EuRoC_ [1] and _TUM-VI_ [2] datasets at this [url](https://cloud.mines-paristech.fr/index.php/s/d2lHqzIk1PxzWmb/download), extract and copy then in the `data` folder.
```
wget "https://cloud.mines-paristech.fr/index.php/s/d2lHqzIk1PxzWmb/download"
unzip download -d denoise-imu-gyro/data
rm download
```
These file can alternatively be generated after downloading the _EuRoC_ and
_TUM-VI_ datasets. They will be generated when lanching the main file after
providing data paths.

2. Download optimized parameters at this [url](https://cloud.mines-paristech.fr/index.php/s/OLnj74YXtOLA7Hv/download), extract and copy in the `results` folder.
```
wget "https://cloud.mines-paristech.fr/index.php/s/OLnj74YXtOLA7Hv/download"
unzip download -d denoise-imu-gyro/results
rm download
```
3. Test on the dataset on your choice !
```
cd denoise-imu-gyro
python3 main_EUROC.py
# or alternatively
# python3 main_TUMVI.py
```

You can then compare results with the evaluation [toolbox](https://github.com/rpng/open_vins/) of [3].

### Training
You can train the method by
uncomment the two lines after # train in the main files. Edit then the
configuration to obtain results with another sets of parameters. It roughly
takes 5 minutes per dataset with a decent GPU.

## Schematic Illustration of the Proposed Method

<p align="center">
<img src="figures/methode.jpg" alt="Schematic illustration of the proposed
method" class="center" width="600"/>
</p>

The convolutional neural network
computes gyro corrections (based on past IMU measurements) that filters
undesirable errors in the raw IMU signals. We
then perform open-loop time integration on the noise-free measurements
for regressing low frequency errors between ground truth and estimated
orientation increments.

## Results

<p align="center">
<img src="figures/rpy.jpg" alt="Orientation estimates"  width="800"/>
</p>

Orientation estimates on the test sequence _MH 04 difficult_ of [1] (left), and
_room 4_ of [2] (right). Our method removes errors of the  IMU.

<p align="center">
<img src="figures/boxplot.jpg" alt="Relative Orientation Error" width="500"/>
</p>

Relative Orientation Error (ROE) in terms of 3D orientation and
yaw errors on the test sequences. Our method competes with VIO methods albeit based only on IMU signals.

## Paper
The paper M. Brossard, S. Bonnabel and A. Barrau, "Denoising IMU Gyroscopes With Deep Learning for Open-Loop Attitude Estimation," in _IEEE Robotics and Automation Letters_, vol. 5, no. 3, pp. 4796-4803, July 2020, doi: 10.1109/LRA.2020.3003256., relative to this repo, is
available at this [url](https://ieeexplore.ieee.org/document/9119813) and a preprint at this [url](https://hal.archives-ouvertes.fr/hal-02488923/document).

## Citation

If you use this code in your research, please cite:

```
@article{brossard2020denoising,
  author={M. {Brossard} and S. {Bonnabel} and A. {Barrau}},
  journal={IEEE Robotics and Automation Letters}, 
  title={Denoising IMU Gyroscopes With Deep Learning for Open-Loop Attitude Estimation}, 
  year={2020},
  volume={5},
  number={3},
  pages={4796-4803},
  }

```

## Authors

This code was written by the [Centre of Robotique](http://caor-mines-paristech.fr/en/home/) at the
MINESParisTech, Paris, France.

[Martin
Brossard](mailto:martin.brossard@mines-paristech.fr)^, [Axel
Barrau](mailto:axel.barrau@safrangroup.com)^ and [Silvère
Bonnabel](mailto:silvere.bonnabel@mines-paristech.fr)^.

^[MINES ParisTech](http://www.mines-paristech.eu/), PSL Research University,
Centre for Robotics, 60 Boulevard Saint-Michel, 75006 Paris, France.

## Biblio

[1] M. Burri, J. Nikolic, P. Gohl, T. Schneider, J. Rehder, S. Omari,
M. W. Achtelik, and R. Siegwart, ``_The EuRoC Micro Aerial Vehicle
Datasets_", The International Journal of Robotics Research, vol. 35,
no. 10, pp. 1157–1163, 2016.

[2] D. Schubert, T. Goll, N. Demmel, V. Usenko, J. Stuckler, and
D. Cremers, ``_The TUM VI Benchmark for Evaluating Visual-Inertial
Odometry_", in International Conference on Intelligent Robots and
Systems (IROS). IEEE, pp. 1680–1687, 2018.

[3] P. Geneva, K. Eckenhoff, W. Lee, Y. Yang, and G. Huang, ``_OpenVINS:
A Research Platform for Visual-Inertial Estimation_", IROS Workshop
on Visual-Inertial Navigation: Challenges and Applications, 2019.

[4] T. Qin, P. Li, and S. Shen, ``_VINS-Mono: A Robust and Versatile
Monocular Visual-Inertial State Estimator_", IEEE Transactions on
Robotics, vol. 34, no. 4, pp. 1004–1020, 2018.

[5] M. Bloesch, M. Burri, S. Omari, M. Hutter, and R. Siegwart, ``_Iterated
Extended Kalman Filter Based Visual-Inertial Odometry Using Direct Photometric
Feedback_", The International Journal of Robotics Research,vol. 36, no. 10, pp.
1053ñ1072, 2017.