ColaSLAM: Real-Time Multi-Robot Collaborative Laser SLAM via Edge Computing

Huang, Peng; Zeng, Liekang; Luo, Ke; Guo, Jinhong; Zhou, Zhi; Chen, Xu

doi:10.1109/iccc52777.2021.9580413

Cited by 11 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… LiDAR-based SLAM for large-scale environments. Faced with large-scale environmental mapping needs, multi-robot cooperative mapping using LiDAR-based SLAM schemes can address the computational load, global error accumulation and risk concentration issues that plague single-robot SLAM (Xie et al , 2022; Chang et al , 2022; Mahboob et al , 2023; Huang et al , 2021). Multi-source fusion-enhanced LiDAR-based SLAM.…”

Section: Challengesmentioning

confidence: 99%

LiDAR-based SLAM for robotic mapping: state of the art and new frontiers

Yue,

Zhang,

Chen

et al. 2024

View full text Add to dashboard Cite

Purpose In recent decades, the field of robotic mapping has witnessed widespread research and development in light detection and ranging (LiDAR)-based simultaneous localization and mapping (SLAM) techniques. This paper aims to provide a significant reference for researchers and engineers in robotic mapping. Design/methodology/approach This paper focused on the research state of LiDAR-based SLAM for robotic mapping as well as a literature survey from the perspective of various LiDAR types and configurations. Findings This paper conducted a comprehensive literature review of the LiDAR-based SLAM system based on three distinct LiDAR forms and configurations. The authors concluded that multi-robot collaborative mapping and multi-source fusion SLAM systems based on 3D LiDAR with deep learning will be new trends in the future. Originality/value To the best of the authors’ knowledge, this is the first thorough survey of robotic mapping from the perspective of various LiDAR types and configurations. It can serve as a theoretical and practical guide for the advancement of academic and industrial robot mapping.

show abstract

Section: Challengesmentioning

confidence: 99%

LiDAR-based SLAM for robotic mapping: state of the art and new frontiers

Yue,

Zhang,

Chen

et al. 2024

View full text Add to dashboard Cite

show abstract

“…Accordingly, one big challenge in centralised and distributed MRSLAM is the constraint on the communication bandwidth, limited computation power, and memory. 5G NR will circumvent these limitations by facilitating edge computing [ 123 , 124 ], providing accurate RF-based measurements, and enabling relative localisation for each vehicle in the team via sidelink and V2V technologies.…”

Section: Future Research Directions and Challengesmentioning

confidence: 99%

A Review of Radio Frequency Based Localisation for Aerial and Ground Robots with 5G Future Perspectives

Kabiri

Cimarelli

Bavle

et al. 2022

Sensors

View full text Add to dashboard Cite

Efficient localisation plays a vital role in many modern applications of Unmanned Ground Vehicles (UGV) and Unmanned Aerial Vehicles (UAVs), which contributes to improved control, safety, power economy, etc. The ubiquitous 5G NR (New Radio) cellular network will provide new opportunities to enhance the localisation of UAVs and UGVs. In this paper, we review radio frequency (RF)-based approaches to localisation. We review the RF features that can be utilized for localisation and investigate the current methods suitable for Unmanned Vehicles under two general categories: range-based and fingerprinting. The existing state-of-the-art literature on RF-based localisation for both UAVs and UGVs is examined, and the envisioned 5G NR for localisation enhancement, and the future research direction are explored.

show abstract

“…This demonstrates the potential benefits of outsourcing SLAM to an edge cloud. Huang et al [59], [60] introduce an algorithm to offload 2D Laser SLAM, whereby the GMapping 2D SLAM system [61], [62] is utilized. They demonstrate that they can speed up processing speed and create joint maps on the edge by using the data of different robots.…”

Section: Related Work On Offloading Slammentioning

confidence: 99%

DynNetSLAM: Dynamic Visual SLAM Network Offloading

et al. 2022

View full text Add to dashboard Cite

Existing Visual Simultaneous Localization And Mapping (vSLAM) approaches that offload the complex self-localization computations from mobile robots over a wireless network to edge computing are limited to static offloading, i.e., the offloaded computation tasks are offloaded permanently. However, wireless networks are inherently dynamic and may excessively delay the transmissions between a mobile device and the edge during periods of poor wireless network quality, e.g., from fading or temporary obstructions. We propose and evaluate Dynamic Visual SLAM Network Offloading (DynNetSLAM) to dynamically adapt the vSLAM computation offloading according to the measured wireless network latency. As groundwork towards developing DynNetSLAM, we first enhance the existing state-of-the-art vSLAM approaches through judicious parameter settings and parallel map updates to enable the tracking of common fast vSLAM data sets. We introduce an offloading latency threshold along with a safe zone and a hysteresis around the threshold to control the dynamic offloading. Our extensive evaluations with public vSLAM data sets indicate that DynNetSLAM with the hysteresis substantially reduces the probability of track loss events compared to the state-of-the-art ORB-SLAM2 approach for processing statically on the mobile device and the enhanced static Edge SLAM. Also, DynNetSLAM nearly attains the low absolute position error and only slightly increases the CPU utilization compared to the enhanced static Edge SLAM.

show abstract

ColaSLAM: Real-Time Multi-Robot Collaborative Laser SLAM via Edge Computing

Cited by 11 publications

References 14 publications

LiDAR-based SLAM for robotic mapping: state of the art and new frontiers

LiDAR-based SLAM for robotic mapping: state of the art and new frontiers

A Review of Radio Frequency Based Localisation for Aerial and Ground Robots with 5G Future Perspectives

DynNetSLAM: Dynamic Visual SLAM Network Offloading

Contact Info

Product

Resources

About