A 4D imaging radar SLAM system for large-scale environments based on pose graph optimization
LiDAR-based SLAM may easily fail in adverse weathers (e.g., rain, snow, smoke, fog), while mmWave Radar remains unaffected. However, current researches are primarily focused on 2D (x,y) or 3D (x,y,doppler) Radar and 3D LiDAR (x,y,z), while limited work can be found for 4D Radar (x,y,z,doppler). As a...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis-Master by Coursework |
| Language: | English |
| Published: |
Nanyang Technological University
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/165315 |
| _version_ | 1824455281413718016 |
|---|---|
| author | Zhuge, Huayang |
| author2 | Wang Dan Wei |
| author_facet | Wang Dan Wei Zhuge, Huayang |
| author_sort | Zhuge, Huayang |
| collection | NTU |
| description | LiDAR-based SLAM may easily fail in adverse weathers (e.g., rain, snow, smoke, fog), while mmWave Radar remains unaffected. However, current researches are primarily focused on 2D (x,y) or 3D (x,y,doppler) Radar and 3D LiDAR (x,y,z), while limited work can be found for 4D Radar (x,y,z,doppler). As a new entrant to the market with unique characteristics, 4D Radar outputs 3D point cloud with added elevation information, rather than 2D point cloud; compared with 3D LiDAR, 4D Radar has noisier and sparser point cloud, making it more challenging to extract geometric features (edge and plane). This work proposes a full system for 4D Radar SLAM consisting of three modules: 1) Front-end module performs scan-to-scan matching to calculate the odometry based on GICP, considering the probability distribution of each point; 2) Loop detection utilizes multiple rule-based loop pre-filtering steps, followed by an intensity scan context step to identify loop candidates, and odometry check to reject false loop; 3) Back-end builds a pose graph using front-end odometry, loop closure, and optional GPS data. Optimal pose is achieved through g2o. Real experiments were conducted on two platforms and five datasets (ranging from 240m to 4.8km) and will make the code open-source to promote further research at: https://github.com/zhuge2333/4DRadarSLAM |
| first_indexed | 2025-02-19T03:35:43Z |
| format | Thesis-Master by Coursework |
| id | ntu-10356/165315 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2025-02-19T03:35:43Z |
| publishDate | 2023 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1653152023-07-04T16:23:17Z A 4D imaging radar SLAM system for large-scale environments based on pose graph optimization Zhuge, Huayang Wang Dan Wei School of Electrical and Electronic Engineering EDWWANG@ntu.edu.sg Engineering::Electrical and electronic engineering::Control and instrumentation::Robotics LiDAR-based SLAM may easily fail in adverse weathers (e.g., rain, snow, smoke, fog), while mmWave Radar remains unaffected. However, current researches are primarily focused on 2D (x,y) or 3D (x,y,doppler) Radar and 3D LiDAR (x,y,z), while limited work can be found for 4D Radar (x,y,z,doppler). As a new entrant to the market with unique characteristics, 4D Radar outputs 3D point cloud with added elevation information, rather than 2D point cloud; compared with 3D LiDAR, 4D Radar has noisier and sparser point cloud, making it more challenging to extract geometric features (edge and plane). This work proposes a full system for 4D Radar SLAM consisting of three modules: 1) Front-end module performs scan-to-scan matching to calculate the odometry based on GICP, considering the probability distribution of each point; 2) Loop detection utilizes multiple rule-based loop pre-filtering steps, followed by an intensity scan context step to identify loop candidates, and odometry check to reject false loop; 3) Back-end builds a pose graph using front-end odometry, loop closure, and optional GPS data. Optimal pose is achieved through g2o. Real experiments were conducted on two platforms and five datasets (ranging from 240m to 4.8km) and will make the code open-source to promote further research at: https://github.com/zhuge2333/4DRadarSLAM Master of Science (Computer Control and Automation) 2023-03-24T00:02:59Z 2023-03-24T00:02:59Z 2023 Thesis-Master by Coursework Zhuge, H. (2023). A 4D imaging radar SLAM system for large-scale environments based on pose graph optimization. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/165315 https://hdl.handle.net/10356/165315 en D-255-21221-03326 application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Electrical and electronic engineering::Control and instrumentation::Robotics Zhuge, Huayang A 4D imaging radar SLAM system for large-scale environments based on pose graph optimization |
| title | A 4D imaging radar SLAM system for large-scale environments based on pose graph optimization |
| title_full | A 4D imaging radar SLAM system for large-scale environments based on pose graph optimization |
| title_fullStr | A 4D imaging radar SLAM system for large-scale environments based on pose graph optimization |
| title_full_unstemmed | A 4D imaging radar SLAM system for large-scale environments based on pose graph optimization |
| title_short | A 4D imaging radar SLAM system for large-scale environments based on pose graph optimization |
| title_sort | 4d imaging radar slam system for large scale environments based on pose graph optimization |
| topic | Engineering::Electrical and electronic engineering::Control and instrumentation::Robotics |
| url | https://hdl.handle.net/10356/165315 |
| work_keys_str_mv | AT zhugehuayang a4dimagingradarslamsystemforlargescaleenvironmentsbasedonposegraphoptimization AT zhugehuayang 4dimagingradarslamsystemforlargescaleenvironmentsbasedonposegraphoptimization |