Coder Social home page Coder Social logo

jason-xy / rio Goto Github PK

View Code? Open in Web Editor NEW

This project forked from hkust-aerial-robotics/rio

2.0 0.0 0.0 15.45 MB

Optimization Based and Point Uncertainty Aware Radar-inertial Odometry for 4D Radar System

License: MIT License

Shell 1.13% C++ 78.02% Python 2.78% CMake 11.01% Dockerfile 7.05%

rio's Introduction

RIO - Complete code will coming soon ...

Optimization Based and Point Uncertainty Aware Radar-inertial Odometry for 4D Radar System

System Overview

Experiment Platform

Our platform consists of a 4D FMCW Radar ARS548RDI manufactured by Continental and an IMU BMI088 manufactured by Bosch. The radar sensor is mounted on the front of the platform, while the IMU is mounted on the bottom.

Trajectories on self-collected and ColoRadar dataset

Red trajectory is the proposed full system. Blue one is the system without point uncertainty model, and black one is the ground truth trajectory. We present the results on four sequences in two different datasets.

Self-collected dataset

  • Sequence 1 : involved relatively low-speed movements.

  • Sequence 2 : involved relatively high-speed movements.

  • Sequence 3 : involved relatively high-speed movements with high-speed rotations.

Data Format

Field Name Data Type Count Offset (Bytes) Remarks
azimuth sensor_msgs::PointField::FLOAT32 1 0 Angle in the horizontal plane
azimuthSTD sensor_msgs::PointField::FLOAT32 1 4 Standard deviation of azimuth
elevation sensor_msgs::PointField::FLOAT32 1 8 Angle in the vertical plane
elevationSTD sensor_msgs::PointField::FLOAT32 1 12 Standard deviation of elevation
range sensor_msgs::PointField::FLOAT32 1 16 Distance to the target
rangeSTD sensor_msgs::PointField::FLOAT32 1 20 Standard deviation of range
velocity sensor_msgs::PointField::FLOAT32 1 24 Speed of the target
velocitySTD sensor_msgs::PointField::FLOAT32 1 28 Standard deviation of velocity
rcs sensor_msgs::PointField::INT8 1 32 Radar cross-section

ColoRadar dataset

It consists of 52 sequences, recorded in mines, built environments, and in an urban creek path, totaling more than 145 minutes of 3D FMCW radar, 3D lidar, and IMU data. The full dataset, including sensor data, calibration sequences, and evaluation scripts. It is available at ColoRadar.

Citation

If you find our work useful in your research, please consider citing:

@article{huang2024morephysicalenhancedradarinertialodometry,
      title={Less is More: Physical-enhanced Radar-Inertial Odometry},
      author={Qiucan Huang and Yuchen Liang and Zhijian Qiao and Shaojie Shen and Huan Yin},
      booktitle={ICRA},
      year={2024},
}
@misc{xu2024modelingpointuncertaintyradar,
      title={Modeling Point Uncertainty in Radar SLAM},
      author={Yang Xu and Qiucan Huang and Shaojie Shen and Huan Yin},
      year={2024},
      eprint={2402.16082},
      archivePrefix={arXiv},
      primaryClass={cs.RO},
      url={https://arxiv.org/abs/2402.16082},
}

License

MIT License (see LICENSE).

rio's People

Contributors

jason-xy avatar

Stargazers

Chen Chao avatar  avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.