Coxgraph: Multi-Robot Collaborative, Globally Consistent, Online Dense Reconstruction System

Liu, Xiangyu; Ye, Weicai; Tian, Chaoran; Cui, Zhaopeng; Bao, Hujun

doi:10.1109/iros51168.2021.9636645

Cited by 8 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nevertheless, the transmission of substantial quantities of dense data continues to pose a significant challenge for multi-robot dense mapping. Enhancing the format of dense data representation has been identified as a viable approach to mitigate communication stress, as suggested by previous studies [10]. In the interim, it is imperative to conduct additional research and investigation into current communication methodologies in order to facilitate the effective transmission of dense data.…”

Section: Multi-robot Slammentioning

confidence: 99%

“…We employed the method proposed in [10] to evaluate the CPU utilization of the front-end system. On the f2/desk dataset, our system was evaluated in comparison to the conventional ORB-SLAM3 and ORB-SLAM algorithms that utilize direct dense mapping.…”

Section: Runtime Performance Analysismentioning

confidence: 99%

“…Dense mapping algorithms currently available often necessitate the use of high-performance GPUs for computation, rendering them unsuitable for implementation in multi-robot systems. Presently, ongoing studies in multi-robot dense mapping primarily concentrate on three areas: task assignment and collaborative path planning [8], dense mapping for distributed robot clusters [9], and dense mapping performed by front-end robots with data compression during transmission [10]. Each of these approaches requires powerful computational and storage capabilities for each robot.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

CMDS-SLAM: real-time efficient centralized multi-robot dense surfel SLAM

Zuo,

Feng,

Xiao

2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Real-time dense mapping technology for multi-robot systems is crucial in scenarios like search and rescue. This paper presents CMDS-SLAM, a centralized multi-robot dense surfel SLAM system aimed at overcoming limitations in hardware constraints, data transmission, and real-time creation and updating of dense maps in multi-robot SLAM. CMDS-SLAM reduces the transmission of dense information by employing a dense information ﬁltering mechanism based on co-visual keyframes, in conjunction with the extraction and compression of superpixels. Additionally, the method employs a three-stage superpixel segmentation approach to optimize transmission and enhance the eﬃciency of surfel map generation. Finally, a surfel co-visibility graph is established, and multi-robot surfel map maintenance and updates are achieved through co-visibility graph and map optimization. A comprehensive evaluation of CMDS-SLAM indicates that the method enables multi-robot surfel mapping and signiﬁcantly alleviates data transmission pressures while achieving real-time updates and maintenance of the surfel map.

show abstract

Section: Multi-robot Slammentioning

confidence: 99%

Section: Runtime Performance Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

CMDS-SLAM: real-time efficient centralized multi-robot dense surfel SLAM

Zuo,

Feng,

Xiao

2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…Most of the existing systems [55]- [59] need to use depth or lidar information for dense reconstruction, this paper does not have this limitation, and can support data formats such as monocular video, stereo, and RGB-D, and can maintain a good reconstruction effect in the dynamic environment. To improve the reconstruction performance, some approaches propose collaborative reconstruction by multiple robots [60]- [62]. As an example, Coxgraph [62] extends the single-robot reconstruction system, Voxgraph [55], to a multi-robot dense reconstruction system, and additionally adds more constraints to ensure low-error reconstruction.…”

Section: Dense Reconstructionmentioning

confidence: 99%

“…To improve the reconstruction performance, some approaches propose collaborative reconstruction by multiple robots [60]- [62]. As an example, Coxgraph [62] extends the single-robot reconstruction system, Voxgraph [55], to a multi-robot dense reconstruction system, and additionally adds more constraints to ensure low-error reconstruction. Our system is able to maintain robust dense reconstruction with less constraint.…”

Section: Dense Reconstructionmentioning

confidence: 99%

DeFlowSLAM: Self-Supervised Scene Motion Decomposition for Dynamic Dense SLAM

Ye¹,

Yu²,

Lan³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

We present a novel dual-flow representation of scene motion that decomposes the optical flow into a static flow field caused by the camera motion and another dynamic flow field caused by the objects' movements in the scene. Based on this representation, we present a dynamic SLAM, dubbed DeFlowSLAM, that exploits both static and dynamic pixels in the images to solve the camera poses, rather than simply using static background pixels as other dynamic SLAM systems do. We propose a dynamic update module to train our DeFlowSLAM in a self-supervised manner, where a dense bundle adjustment layer takes in estimated static flow fields and the weights controlled by the dynamic mask and outputs the residual of the optimized static flow fields, camera poses, and inverse depths. The static and dynamic flow fields are estimated by warping the current image to the neighboring images, and the optical flow can be obtained by summing the two fields. Extensive experiments demonstrate that DeFlowSLAM generalizes well to both static and dynamic scenes as it exhibits comparable performance to the state-ofthe-art DROID-SLAM in static and less dynamic scenes while significantly outperforming DROID-SLAM in highly dynamic environments. Code and data are available on the project webpage: https://zju3dv.github.io/deflowslam/.

show abstract

Collaborative SLAM System Based on Shared Priori Maps

Shou

et al. 2023

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

Coxgraph: Multi-Robot Collaborative, Globally Consistent, Online Dense Reconstruction System

Cited by 8 publications

References 17 publications

CMDS-SLAM: real-time efficient centralized multi-robot dense surfel SLAM

CMDS-SLAM: real-time efficient centralized multi-robot dense surfel SLAM

DeFlowSLAM: Self-Supervised Scene Motion Decomposition for Dynamic Dense SLAM

Collaborative SLAM System Based on Shared Priori Maps

Contact Info

Product

Resources

About