ART-SLAM: Accurate Real-Time 6DoF LiDAR SLAM

Frosi, Matteo; Matteucci, Matteo

doi:10.1109/lra.2022.3144795

Cited by 26 publications

(30 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…LeGO-LOAM-BOR and LIO-SAM are designed to perform real-time SLAM, with the latter being even faster (the average processing time ranges from 35 to 50 milliseconds). Moreover, as described in [7], also ART-SLAM is able to achieve real-time results, even on long sequences. Table III shows the average processing time, per frame, of MCS-SLAM, in all five scenarios considered in the evaluation, for both sequences.…”

Section: A Comparison and Resultsmentioning

confidence: 94%

“…The proposed system has been compared against four methods for point cloud-based SLAM: LeGO-LOAM-BOR (which is an improved variant of LeGO-LOAM [4]), LIO-SAM [5], HDL [6] and ART-SLAM [7]. IMU data, which is mandatory in LIO-SAM, is also used in ART-SLAM, to deskew point clouds and to enforce rotational constraints in the pose graph.…”

Section: Experimental Validation Of the Systemmentioning

confidence: 99%

“…Some systems, such as LeGO-LOAM [4] and LIO-SAM [5], perform scan matching by comparing 3D features extracted from point clouds, including edges, planes or clusters, with the latter also requiring high frequency IMU data. Other methods, including HDL [6] and the very recent ART-SLAM [7], perform, instead, scan matching on full point clouds (or a downsampled version), evaluating the point-to-point alignment. Feature-based systems are less accurate than full point cloud-based methods, although they are faster.…”

Section: Introductionmentioning

confidence: 99%

“…Fig.6. Comparison between the trajectories estimated by LeGO-LOAM-BOR (derived from LeGO-LOAM[4]), HDL[6], ART-SLAM[7] and the proposed system (in the multiple sensors scenarios), on City Sequence 05 of the KITTI raw dataset[16]. The other methods considered in the evaluation are not included, to avoid further overlapping.…”

mentioning

confidence: 99%

See 3 more Smart Citations

MCS-SLAM: Multi-Cues Multi-Sensors Fusion SLAM

Frosi

Matteucci

2022

2022 IEEE Intelligent Vehicles Symposium (IV)

Self Cite

View full text Add to dashboard Cite

Simultaneous localization and mapping (SLAM) is one fundamental topic in robotics due to its applications in autonomous driving. Over the last decades, many systems have been proposed, working on data coming from different sensors, such as cameras or LiDARs. Although excellent results were reached, the majority of these methods exploit the data as is, without extracting additional information or considering multiple sensors simultaneously. In this paper, we present MCS-SLAM, a Graph SLAM system that performs sensor fusion by exploiting multi-cues extracted from sensor data: color/intensity, depth/range and normal information. For each sensor, motion estimation is achieved through minimization of the pixel-wise difference between two multi-cue images. All estimates are then collectively optimized to achieve a coherent transformation. Point clouds received as input are also used to perform loop detection and closure. We compare the performance of the proposed system with state-of-theart point cloud-based methods, LeGO-LOAM-BOR, LIO-SAM, HDL and ART-SLAM, and show that the proposed algorithm achieves less accuracy than the state-of-the-art, while needing much less computational time. The comparison is made by evaluating the estimated trajectory displacement, using the KITTI dataset.

show abstract

Section: A Comparison and Resultsmentioning

confidence: 94%

Section: Experimental Validation Of the Systemmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

MCS-SLAM: Multi-Cues Multi-Sensors Fusion SLAM

Frosi

Matteucci

2022

2022 IEEE Intelligent Vehicles Symposium (IV)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Several previous lidar SLAM studies have evaluated and compared the accuracy between different methods including recent both outdoor [13,29] and indoor [39] applications. To our knowledge, no previous study has addressed or quantified the specific accuracy performance or degradation when passing through narrow openings and we thus consider our study a relevant contribution also in this aspect.…”

Section: Related Workmentioning

confidence: 99%

Lidar Positioning for Indoor Precision Navigation

Holmberg

Karlsson

Tulldahl

2022

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

Lidar based simultaneous localization and mapping methods can be adapted for deployment on small autonomous vehicles operating in unmapped indoor environments. For this purpose, we propose a method which combines inertial data, low-drift lidar odometry, planar primitives, and loop closing in a graph-based structure. The accuracy of our method is experimentally evaluated, using a high-resolution lidar, and compared to the state-ofthe-art methods LIO-SAM and Cartographer. We specifically address the lateral positioning accuracy when passing through narrow openings, where high accuracy is a prerequisite for safe operation of autonomous vehicles. The test cases include doorways, slightly wider reference passages, and a larger corridor environment. We observe a reduced lateral accuracy for all three methods when passing through the narrow openings compared to operation in larger spaces. Compared to state-of-the-art, our method shows better results in the narrow passages, and comparable results in the other environments with reasonably low usage of CPU and memory resources.

show abstract

MLIO: Multiple LiDARs and Inertial Odometry

Dahal,

Arrigoni,

Bijelic

et al. 2024

Lecture Notes in Mechanical Engineering

View full text Add to dashboard Cite

With the decreasing cost of LiDAR sensors, sensor setups with multiple LiDARs are becoming available. In such advanced setups with multiple LiDARs the sensor temporal asynchronicity and spatial miscalibration are critical factors for vehicle localization increasing measurement uncertainty. Hence, simple merging of synchronized point clouds as done in some literature can lead to sub-optimal results. To tackle this problem we propose MLIO, a factor graph-based odometry computation algorithm that fuses multiple LiDARs with an inertial measurement unit (IMU) and provides an accurate solution mitigating the effect of temporal asynchronisity and spatial miscalibration.The proposed algorithm is validated using a custom dataset. We compare the proposed algorithm with the state-of-the-art LiDAR-only odometry algorithms, such as KISS-ICP, and LiDAR-IMU fusion LIO-SAM and demonstrate its superiority. We were able to achieve up to 40% and 16% increment in positional and orientation accuracy compared to KISS-ICP and 25% increment in positional accuracy compared to LIO-SAM.

show abstract

ART-SLAM: Accurate Real-Time 6DoF LiDAR SLAM

Cited by 26 publications

References 18 publications

MCS-SLAM: Multi-Cues Multi-Sensors Fusion SLAM

MCS-SLAM: Multi-Cues Multi-Sensors Fusion SLAM

Lidar Positioning for Indoor Precision Navigation

MLIO: Multiple LiDARs and Inertial Odometry

Contact Info

Product

Resources

About