kRadar++: Coarse-to-Fine FMCW Scanning Radar Localisation
This paper presents a novel two-stage system which integrates topological localisation candidates from a radar-only place recognition system with precise pose estimation using spectral landmark-based techniques. We prove that the—recently available—seminal radar place recognition (RPR) and scan matc...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-10-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/21/6002 |
| _version_ | 1827703743306530816 |
|---|---|
| author | Daniele De Martini Matthew Gadd Paul Newman |
| author_facet | Daniele De Martini Matthew Gadd Paul Newman |
| author_sort | Daniele De Martini |
| collection | DOAJ |
| description | This paper presents a novel two-stage system which integrates topological localisation candidates from a radar-only place recognition system with precise pose estimation using spectral landmark-based techniques. We prove that the—recently available—seminal radar place recognition (RPR) and scan matching sub-systems are complementary in a style reminiscent of the mapping and localisation systems underpinning visual teach-and-repeat (VTR) systems which have been exhibited robustly in the last decade. Offline experiments are conducted on the most extensive radar-focused urban autonomy dataset available to the community with performance comparing favourably with and even rivalling alternative state-of-the-art radar localisation systems. Specifically, we show the long-term durability of the approach and of the sensing technology itself to autonomous navigation. We suggest a range of sensible methods of tuning the system, all of which are suitable for online operation. For both tuning regimes, we achieve, over the course of a month of localisation trials against a single static map, high recalls at high precision, and much reduced variance in erroneous metric pose estimation. As such, this work is a necessary first step towards a radar teach-and-repeat (RTR) system and the enablement of autonomy across extreme changes in appearance or inclement conditions. |
| first_indexed | 2024-03-10T15:24:11Z |
| format | Article |
| id | doaj.art-f9a2b2d896e7468595e082c549ce0797 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T15:24:11Z |
| publishDate | 2020-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-f9a2b2d896e7468595e082c549ce07972023-11-20T18:12:45ZengMDPI AGSensors1424-82202020-10-012021600210.3390/s20216002kRadar++: Coarse-to-Fine FMCW Scanning Radar LocalisationDaniele De Martini0Matthew Gadd1Paul Newman2Department of Engineering Science, Oxford Robotics Institute, University of Oxford, Oxford OX1 3PJ, UKDepartment of Engineering Science, Oxford Robotics Institute, University of Oxford, Oxford OX1 3PJ, UKDepartment of Engineering Science, Oxford Robotics Institute, University of Oxford, Oxford OX1 3PJ, UKThis paper presents a novel two-stage system which integrates topological localisation candidates from a radar-only place recognition system with precise pose estimation using spectral landmark-based techniques. We prove that the—recently available—seminal radar place recognition (RPR) and scan matching sub-systems are complementary in a style reminiscent of the mapping and localisation systems underpinning visual teach-and-repeat (VTR) systems which have been exhibited robustly in the last decade. Offline experiments are conducted on the most extensive radar-focused urban autonomy dataset available to the community with performance comparing favourably with and even rivalling alternative state-of-the-art radar localisation systems. Specifically, we show the long-term durability of the approach and of the sensing technology itself to autonomous navigation. We suggest a range of sensible methods of tuning the system, all of which are suitable for online operation. For both tuning regimes, we achieve, over the course of a month of localisation trials against a single static map, high recalls at high precision, and much reduced variance in erroneous metric pose estimation. As such, this work is a necessary first step towards a radar teach-and-repeat (RTR) system and the enablement of autonomy across extreme changes in appearance or inclement conditions.https://www.mdpi.com/1424-8220/20/21/6002radarmappinglocalisationplace recognitionautonomous vehiclesdeep learning |
| spellingShingle | Daniele De Martini Matthew Gadd Paul Newman kRadar++: Coarse-to-Fine FMCW Scanning Radar Localisation Sensors radar mapping localisation place recognition autonomous vehicles deep learning |
| title | kRadar++: Coarse-to-Fine FMCW Scanning Radar Localisation |
| title_full | kRadar++: Coarse-to-Fine FMCW Scanning Radar Localisation |
| title_fullStr | kRadar++: Coarse-to-Fine FMCW Scanning Radar Localisation |
| title_full_unstemmed | kRadar++: Coarse-to-Fine FMCW Scanning Radar Localisation |
| title_short | kRadar++: Coarse-to-Fine FMCW Scanning Radar Localisation |
| title_sort | kradar coarse to fine fmcw scanning radar localisation |
| topic | radar mapping localisation place recognition autonomous vehicles deep learning |
| url | https://www.mdpi.com/1424-8220/20/21/6002 |
| work_keys_str_mv | AT danieledemartini kradarcoarsetofinefmcwscanningradarlocalisation AT matthewgadd kradarcoarsetofinefmcwscanningradarlocalisation AT paulnewman kradarcoarsetofinefmcwscanningradarlocalisation |