Point Wise or Feature Wise? A Benchmark Comparison of Publicly Available Lidar Odometry Algorithms in Urban Canyons

Huang, Feng; Wen, Weisong; Zhang, Jiachen; Hsu, Li‐Ta

doi:10.1109/mits.2021.3092731

Cited by 23 publications

(8 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The second step matches the current scan and the point cloud map (scan-to-map) to mitigate the error estimation arising from scan-to-scan. According to our previous research [29], this computational load and accuracy of LOAM outperform other methods in highly urbanized areas.…”

Section: Pv-rcnn Training and Detectionsupporting

confidence: 52%

See 1 more Smart Citation

A Coarse-to-Fine LiDAR-Based SLAM with Dynamic Object Removal in Dense Urban Areas

Huang¹,

Dong-hui²,

Wen³

et al. 2021

Proceedings of the 34th International Technical Meeting of the Satellite Division of the Institute of Navigation (ION GNSS+ 202

Self Cite

View full text Add to dashboard Cite

His research interests including localization and sensor fusion for autonomous driving.Shen Donghui received his bachelor's degree from Shandong University in Space Science and Technology in 2017 and MSc in Space Physics at Shandong University in 2020. His research interests including 3D perception and HD Map updating for autonomous driving.Weisong Wen was born in Ganzhou, Jiangxi, China. He received a Ph.D. degree in mechanical engineering, the Hong Kong Polytechnic University, in 2020. He is currently a senior research fellow at the Hong Kong Polytechnic University. His research interests include multi-sensor integrated localization for autonomous vehicles, SLAM, and GNSS positioning in urban canyons. He was a visiting student researcher at the University of California, Berkeley (UCB) in 2018.ZHANG Jiachen received her bachelor's degree from Tianjin University in Information Engineering in 2016 and is currently an enrolled, full-time graduate student at Tianjin University, majoring in Optical Engineering. She is working as a research assistant in the Intelligent Positioning and Navigation Laboratory. Her research interests including localization and sensor fusion for autonomous driving.Li-Ta Hsu received the B.S. and Ph.D. degrees in aeronautics and astronautics from National Cheng Kung University, Taiwan, in 2007 and 2013, respectively. He is currently an assistant professor with the Division of Aeronautical and Aviation Engineering, Hong Kong Polytechnic University, before he served as post-doctoral researcher in Institute of Industrial Science at University of Tokyo, Japan. In 2012, he was a visiting scholar in University College London, U.K. He was a technical representative in ION in 2019-2021 and is an Associate Fellow of RIN. His research interests include GNSS positioning in challenging environments and localization for pedestrian, autonomous driving vehicle and unmanned aerial vehicle.

show abstract

Section: Pv-rcnn Training and Detectionsupporting

confidence: 52%

“…We labeled the dynamic objects such as cars and buses in the datasets to explore how the dynamic objects affecting the position error. The density of dynamic objects factor [29] is defined as,…”

Section: Lidar Odometrymentioning

confidence: 99%

A Coarse-to-Fine LiDAR-Based SLAM with Dynamic Object Removal in Dense Urban Areas

Huang¹,

Dong-hui²,

Wen³

et al. 2021

Proceedings of the 34th International Technical Meeting of the Satellite Division of the Institute of Navigation (ION GNSS+ 202

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Robot Pose Estimationmentioning

confidence: 99%

“…This section discusses the results obtained comparing different pose estimation algorithms. For this purpose, we selected a set of approaches among the most popular for both vision‐based (see Legittimo et al, 2023) and LIDAR‐based (see Huang et al, 2022; Jonnavithula et al, 2021) pose estimation. In particular, we considered: Direct Sparse Odometry (DSO) (Engel et al, 2017) and ORB‐SLAM2 Mono (Mur‐Artal & Tardós, 2017) for monocular camera setups; VINS‐Mono (Qin et al, 2018) for monocular‐inertial setups; ORB‐SLAM2 Stereo (Mur‐Artal & Tardós, 2017) for stereo‐camera setups; Open‐VINS (Geneva et al, 2020) for stereo‐inertial setups; FLOAM (Wang et al, 2020) and LeGO‐LOAM (Shan & Englot, 2018) for LIDAR‐based setups.We performed comparative experiments on a selection of eight sequences, considering two sequences for each cultivation field.…”

Section: Applicationsmentioning

confidence: 99%

ARD‐VO: Agricultural robot data set of vineyards and olive groves

Crocetti

Bellocchio

Dionigi

et al. 2023

Journal of Field Robotics

View full text Add to dashboard Cite

The availability of real-world data in agricultural applications is of paramount importance to develop robust and effective robotic-based solutions for farming operations. In this application context, however, very few data sets are available to the community and for some important crops, such as grapes and olives, they are almost absent. Therefore, the aim of this paper is to introduce and release ARD-VO, a data set for agricultural robotics applications focused on vineyards and olive cultivations. Its main purpose is to provide the researchers with a real-world extensive set of data to support the development of solutions and algorithms for precision farming technologies in the aforementioned crops.ARD-VO has been collected with an unmanned ground vehicle (UGV) equipped with different heterogeneous sensors that capture information essential for robot localization and plant monitoring tasks. It is composed of sequences gathered in 11 experimental sessions between August and October 2021, navigating the UGV for several kilometers in four cultivation fields in Umbria, a central region of Italy. In addition, to highlight the utility of ARD-VO, two application case studies are presented. In the first one, the data set is used to compare the performance of simultaneous localization and mapping and odometry estimation methods using vision systems, light detection and ranging, and inertial measurement unit sensors. The second one shows how the multispectral images included in ARD-VO can be used to compute Normalized Difference Vegetation Index maps, which are crucial to monitor the crops and build prescription maps.

show abstract

“…According to a recent evaluation in [24], better positioning accuracy and robustness are obtained based on the assessment using typical autonomous driving datasets collected by the 360 • rotating mechanical LiDAR. As a result, the NDT-based map matching was employed in a wide range of autonomous driving applications [25][26][27][28]. Unfortunately, all these LiDAR matching-based localization mainly relied on the mechanical 3D LiDAR which is too expensive for massive deployment in ADVs.…”

Section: Related Workmentioning

confidence: 99%

Low‐cost solid‐state LiDAR/inertial‐based localization with prior map for autonomous systems in urban scenarios

Zhong

Huang

Zhang

et al. 2022

IET Intelligent Trans Sys

Self Cite

View full text Add to dashboard Cite

A low‐cost and accurate positioning solution is significant for the massive deployment of fully autonomous driving vehicles (ADV). Conventional mechanical LiDAR has proven its performance, but its high cost hinders the massive production of autonomous vehicles. This paper proposes a low‐cost LiDAR/inertial‐based localization solution for autonomous systems with prior maps in urban areas. Instead of relying on the costly mechanical LiDAR, this paper proposes to utilize the solid‐state LiDAR (SSL) with the prior map to estimate the position of the vehicle by matching the real‐time point clouds from the SSL and the prior map using the normal distribution transformation (NDT) algorithm. However, the field of view (FOV) of the SSL is signifcantly smaller than the conventional mechanical LiDAR, which can easily lead to failure during the NDT map matching. To fill this gap, this paper proposes to exploit the complementariness of the inertial measurement unit (IMU) and the SSL, where the IMU pre‐integration provides a coarse but high‐frequency initial guess to the map matching. To evaluate the effectiveness of the proposed method in this paper, the authors collect the dataset in two typical urban scenarios through a pedestrian hand‐hold and a vehicle driving condition. The results reveal that the SSL‐only‐based localization is significantly challenged in dynamic scenarios. With the help of the IMU, the robustness of the proposed method is significantly improved, achieving an accuracy of within 0.5 m. To show the sensitivity of the SSL‐based map matching against the initial guess of the state, this paper also presents the convergence results of the map matching under different levels of accuracy in terms of the initial guess.

show abstract

Point Wise or Feature Wise? A Benchmark Comparison of Publicly Available Lidar Odometry Algorithms in Urban Canyons

Cited by 23 publications

References 47 publications

A Coarse-to-Fine LiDAR-Based SLAM with Dynamic Object Removal in Dense Urban Areas

A Coarse-to-Fine LiDAR-Based SLAM with Dynamic Object Removal in Dense Urban Areas

ARD‐VO: Agricultural robot data set of vineyards and olive groves

Low‐cost solid‐state LiDAR/inertial‐based localization with prior map for autonomous systems in urban scenarios

Contact Info

Product

Resources

About