LVI-SAM: Tightly-coupled Lidar-Visual-Inertial Odometry via Smoothing and Mapping

Shan, Tixiao; Englot, Brendan; Ratti, Carlo; Rus, Daniela

doi:10.1109/icra48506.2021.9561996

Cited by 177 publications

(70 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Focusing on LiDAR SLAM, similarly to LOAM and its variants [11], [12], methods like LIO-SAM [13], LIO-MAPPING [14], HDL-SLAM [3] also estimate the robot poses and a 3D map, but with option of integrating additional sensor modalities such as IMU and GPS. Other methods such as like LIMO [15], LIRO [16] and LVI-SLAM [17] fuse visual and LiDAR measurements for simultaneous localization and mapping. Although these systems demonstrated significant progress in robustness and accuracy in the last years, they are limited for several application cases by their map representation.…”

Section: Related Workmentioning

confidence: 99%

Situational Graphs for Robot Navigation in Structured Indoor Environments

Bavle¹,

Sánchez-López²,

Shaheer³

et al. 2022

Preprint

View full text Add to dashboard Cite

Autonomous mobile robots should be aware of their situation, understood as a comprehensive understanding of the environment along with the estimation of its own state, to successfully make decisions and execute tasks in natural environments. 3D scene graphs are an emerging field of research with great potential to represent these situations in a joint model comprising geometric, semantic and relational/topological dimensions. Although 3D scene graphs have already been utilized for this, further research is still required to effectively deploy them on-board mobile robots.To this end, we present in this paper a real-time online built Situational Graphs (S-Graphs), composed of a single graph representing the environment, while simultaneously improving the robot pose estimation. Our method utilizes odometry readings and planar surfaces extracted from 3D LiDAR scans, to construct and optimize in real-time a three layered S-Graph that includes a robot tracking layer where the robot poses are registered, a metric-semantic layer with features such as planar walls and our novel topological layer constraining higher-level features such as corridors and rooms. Our proposal does not only demonstrate state-of-the-art results for pose estimation of the robot, but also contributes with a metric-semantictopological model of the environment.

show abstract

Section: Related Workmentioning

confidence: 99%

Situational Graphs for Robot Navigation in Structured Indoor Environments

Bavle¹,

Sánchez-López²,

Shaheer³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…However they require hardware-synchronized camera-lidar messages, which can only produce very low rate data. In [2], Shan et al proposed a loose integration of VIO output from VINS-Mono [11] to LIO-SAM [12], which itself loosely integrates LeGO-LOAM output [13] with IMU preintegration, in a gtsam pose-graph optimization framework. This approach can be unreliable as the whole chain depends on whether the core lidar-based process runs well.…”

Section: Related Workmentioning

confidence: 99%

“…If there is a low-texture case when lidar localization is unstable, its error can reverberate up the chain, which appears to be the case in some of our experiments that will be presented in later parts. We also note that the aforementioned works [1], [2], [9], [10], [12], [13] do not consider the integration of multiple lidars. While the MLOAM method [14] addresses this issue, it focuses purely on lidar and no camera and IMU is involved.…”

Section: Related Workmentioning

confidence: 99%

“…For example, since lidar is not affected by lighting condition or lack of visual features, which can easily destabilize most visual-inertial-odometry (VIO) systems, the robot can still rely on this type of sensor for localization in low light or low-texture conditions. In addition, camera can also enable loop closure capability, while lidar pointcloud map can help augment the visual feature's depth estimation process [1], [2]. This is one of the main advantages that motivates us to develop a tightly coupled camera-lidar-IMUbased Simultaneous Localization and Mapping (SLAM) system in this paper.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

VIRAL SLAM: Tightly Coupled Camera-IMU-UWB-Lidar SLAM

Nguyen,

Yuan,

Cao

et al. 2021

Preprint

View full text Add to dashboard Cite

In this paper, we propose a tightly-coupled, multimodal simultaneous localization and mapping (SLAM) framework, integrating an extensive set of sensors: IMU, cameras, multiple lidars, and Ultra-wideband (UWB) range measurements, hence referred to as VIRAL (visual-inertial-ranginglidar) SLAM. To achieve such a comprehensive sensor fusion system, one has to tackle several challenges such as data synchronization, multi-threading programming, bundle adjustment (BA), and conflicting coordinate frames between UWB and the onboard sensors, so as to ensure real-time localization and smooth updates in the state estimates.To this end, we propose a two stage approach. In the first stage, lidar, camera, and IMU data on a local sliding window are processed in a core odometry thread. From this local graph, new key frames are evaluated for admission to a global map. Visual feature-based loop closure is also performed to supplement the global factor graph with loop constraints. When the global factor graph satisfies a condition on spatial diversity, the BA process will be triggered, which updates the coordinate transform between UWB and onboard SLAM systems. The system then seamlessly transitions to the second stage where all sensors are tightly integrated in the odometry thread. The capability of our system is demonstrated via several experiments on high-fidelity graphical-physical simulation and public datasets.

show abstract

“…Lidar odometry and SLAM for creating metric maps has been widely researched in robotics to create metric maps of the environment such as Cartographer [139], Hector-SLAM [140] performing a complete SLAM using 2D lidar measurements and LOAM [141] providing a parallel lidar odometry and mapping technique to simultaneously compute the lidar velocity while creating accurate 3D maps of the environment. To further improve the accuracy, techniques have been presented which combine vision and lidar measurement as in Lidar-Monocular Visual Odometry (LIMO) [142], LVI-SLAM [143] combining robust monocular image tracking with precise depth estimates from lidar measurements for motion estimation. Methods like LIRO [144], VIRAL-SLAM [145], couple additional measurements like Ultra Wide Band (UWB) with visual and IMU sensors for robust pose estimation and map building.…”

Section: B Localization and Scene Modelingmentioning

confidence: 99%

From SLAM to Situational Awareness: Challenges and Survey

Bavle¹,

Sánchez-López²,

Cimarelli³

et al. 2021

Preprint

View full text Add to dashboard Cite

The knowledge that an intelligent and autonomous mobile robot has and is able to acquire of itself and the environment, namely the situation, limits its reasoning, decision-making, and execution skills to efficiently and safely perform complex missions. Situational awareness is a basic capability of humans that has been deeply studied in fields like Psychology, Military, Aerospace, Education, etc., but it has barely been considered in robotics, which has focused on ideas such as sensing, perception, sensor fusion, state estimation, localization and mapping, spatial AI, etc. In our research, we connected the broad multidisciplinary existing knowledge on situational awareness with its counterpart in mobile robotics. In this paper, we survey the state-of-the-art robotics algorithms, we analyze the situational awareness aspects that have been covered by them, and we discuss their missing points. We found out that the existing robotics algorithms are still missing manifold important aspects of situational awareness. As a consequence, we conclude that these missing features are limiting the performance of robotic situational awareness, and further research is needed to overcome this challenge. We see this as an opportunity, and provide our vision for future research on robotic situational awareness.

show abstract

LVI-SAM: Tightly-coupled Lidar-Visual-Inertial Odometry via Smoothing and Mapping

Cited by 177 publications

References 20 publications

Situational Graphs for Robot Navigation in Structured Indoor Environments

Situational Graphs for Robot Navigation in Structured Indoor Environments

VIRAL SLAM: Tightly Coupled Camera-IMU-UWB-Lidar SLAM

From SLAM to Situational Awareness: Challenges and Survey

Contact Info

Product

Resources

About