Radar-to-Lidar: Heterogeneous Place Recognition via Joint Learning

Yin, Huan; Xu, Xuecheng; Wang, Yue; Xiong, Rong

doi:10.3389/frobt.2021.661199

Cited by 20 publications

(37 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3. Recent spinning radars without Doppler measurements have demonstrated high range, accuracy, and richness and have inspired numerous methods; from odometry estimation and alignment quality assessment to global localization [10], [14], [40]- [44], localization in previous maps [41] and SLAM [2], [15].…”

Section: Related Workmentioning

confidence: 99%

Lidar-Level Localization With Radar? The CFEAR Approach to Accurate, Fast, and Robust Large-Scale Radar Odometry in Diverse Environments

Adolfsson¹,

Magnusson²,

Alhashimi³

et al. 2023

IEEE Trans. Robot.

View full text Add to dashboard Cite

This paper presents an accurate, highly efficient, and learning-free method for large-scale odometry estimation using spinning radar, empirically found to generalize well across very diverse environments -outdoors, from urban to woodland, and indoors in warehouses and mines -without changing parameters. Our method integrates motion compensation within a sweep with one-to-many scan registration that minimizes distances between nearby oriented surface points and mitigates outliers with a robust loss function. Extending our previous approach CFEAR, we present an in-depth investigation on a wider range of data sets, quantifying the importance of filtering, resolution, registration cost and loss functions, keyframe history, and motion compensation. We present a new solving strategy and configuration that overcomes previous issues with sparsity and bias, and improves our state-of-the-art by 38%, thus, surprisingly, outperforming radar SLAM and approaching lidar SLAM. The most accurate configuration achieves 1.09% error at 5 Hz on the Oxford benchmark, and the fastest achieves 1.79% error at 160 Hz.

show abstract

Section: Related Workmentioning

confidence: 99%

Lidar-Level Localization With Radar? The CFEAR Approach to Accurate, Fast, and Robust Large-Scale Radar Odometry in Diverse Environments

Adolfsson¹,

Magnusson²,

Alhashimi³

et al. 2023

IEEE Trans. Robot.

View full text Add to dashboard Cite

show abstract

“…[25], a full radar SLAM system was presented, which includes both odometry module and loop closing module for local and global pose estimation, respectively. Considering that precise radar mapping remains difficult and challenging, researchers proposed to localise the radar sensor on other modalities, such as Google satellite images [26] and lidar maps [26–29]. These methods mainly focus on cross‐modality localisation, and deep neural networks are built to achieve multiple modalities matching.…”

Section: Related Workmentioning

confidence: 99%

“…In summary, compared to radar odometry‐based pose tracking [21–24], the proposed radar‐based localisation can improve pose estimation for long‐distance travelling. As for long‐term running, localisation on maps [26–29] is a more efficient and applicable solution compared to radar SLAM [25]. In Ref.…”

Section: Related Workmentioning

confidence: 99%

“…Lidar maps were also built for radar‐based pose tracking and place recognition in Ref. [16, 27] respectively. This paper is an extension of Ref.…”

Section: Related Workmentioning

confidence: 99%

“…In Ref. [26, 27], researchers presented a learnt localisation method across sensor modalities, but the back‐end estimator was not designed in these two papers. The goal of this paper is same as our previous study RaLL [28, 29], but the methods are distinctly different from both feature extraction at the front‐end and estimator at the back‐end.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Radar style transfer for metric robot localisation on lidar maps

Yin

Wang

et al. 2022

CAAI Trans on Intel Tech

Self Cite

View full text Add to dashboard Cite

Lidar and visual data are affected heavily in adverse weather conditions due to sensing mechanisms, which bring potential safety hazards for vehicle navigation. Radar sensing is desirable to build a more robust navigation system. In this paper, a cross-modality radar localisation on prior lidar maps is presented. Specifically, the proposed workflow consists of two parts: first, bird's-eye-view radar images are transferred to fake lidar images by training a generative adversarial network offline. Then with online radar scans, a Monte Carlo localisation framework is built to track the robot pose on lidar maps. The whole online localisation system only needs a rotating radar sensor and a pre-built global lidar map. In the experimental section, the authors conduct an ablation study on image settings and test the proposed system on Oxford Radar Robot Car Dataset. The promising results show that the proposed localisation system could track the robot pose successfully, thus demonstrating the feasibility of radar style transfer for metric robot localisation on lidar maps.

show abstract

A systematic literature review on long‐term localization and mapping for mobile robots

Sousa

Sobreira

Moreira

2023

Journal of Field Robotics

View full text Add to dashboard Cite

Long‐term operation of robots creates new challenges to Simultaneous Localization and Mapping (SLAM) algorithms. Long‐term SLAM algorithms should adapt to recent changes while preserving older states, when dealing with appearance variations (lighting, daytime, weather, or seasonal) or environment reconfiguration. When also operating robots for long periods and trajectory lengths, the map should readjust to environment changes but not grow indefinitely. The map size should depend only on updating the map with new information of interest, not on the operation time or trajectory length. Although several studies in the literature review SLAM algorithms, none of the studies focus on the challenges associated to lifelong SLAM. Thus, this paper presents a systematic literature review on long‐term localization and mapping following the Preferred Reporting Items for Systematic reviews and Meta‐Analysis guidelines. The review analyzes 142 works covering appearance invariance, modeling the environment dynamics, map size management, multisession, and computational topics such as parallel computing and timing efficiency. The analysis also focus on the experimental data and evaluation metrics commonly used to assess long‐term autonomy. Moreover, an overview over the bibliographic data of the 142 records provides analysis in terms of keywords and authorship co‐occurrence to identify the terms more used in long‐term SLAM and research networks between authors, respectively. Future studies can update this paper thanks to the systematic methodology presented in the review and the public GitHub repository with all the documentation and scripts used during the review process.

show abstract

Radar-to-Lidar: Heterogeneous Place Recognition via Joint Learning

Cited by 20 publications

References 43 publications

Lidar-Level Localization With Radar? The CFEAR Approach to Accurate, Fast, and Robust Large-Scale Radar Odometry in Diverse Environments

Lidar-Level Localization With Radar? The CFEAR Approach to Accurate, Fast, and Robust Large-Scale Radar Odometry in Diverse Environments

Radar style transfer for metric robot localisation on lidar maps

A systematic literature review on long‐term localization and mapping for mobile robots

Contact Info

Product

Resources

About