Uploaded February 2013 | Updated November 2026, 42 minutes ago
This video presents a study case for local point cloud registration. A Search & Rescue robot is used to move around a train surrounded by vegetations.
All the 3D mapping are real-time and realized using the open-source library "libpointmatcher":
github.com/ethz-asl/libpointmatcher
The library has a ROS interface to ease deployment on multiple robotic platforms:
ros.org/wiki/ethzasl_icp_mapper
The performance and capabilities of the library were presented in:
F. Pomerleau, F. Colas, R. Siegwart, and S. Magnenat, "Comparing ICP Variants on Real-World Data Sets," Autonomous Robots
link.springer.com/article/10.1007%2Fs10514-013-9327-2
This video presents a study case for local point cloud registration. A Search & Rescue robot is used to move around a train surrounded by vegetations.
All the 3D mapping are real-time and realized using the open-source library "libpointmatcher":
github.com/ethz-asl/libpointmatcher
The library has a ROS interface to ease deployment on multiple robotic platforms:
ros.org/wiki/ethzasl_icp_mapper
The performance and capabilities of the library were presented in:
F. Pomerleau, F. Colas, R. Siegwart, and S. Magnenat, "Comparing ICP Variants on Real-World Data Sets," Autonomous Robots
link.springer.com/article/10.1007%2Fs10514-013-9327-2
![[ICRA22] Collaborative Robot Mapping using Spectral Graph Analysis
ArXiv: https://arxiv.org/abs/2203.00308
Github: https://github.com/ethz-asl/fgsp
Contact: Lukas Bernreiter berlukas@ethz.ch
Abstract:
In this paper, we deal with the problem of creating globally consistent pose graphs in a centralized multi-robot SLAM framework.
For each robot to act autonomously, individual onboard pose estimates and maps are maintained, which are then communicated to a central server to build an optimized global map.
However, inconsistencies between onboard and server estimates can occur due to onboard odometry drift or failure.
Furthermore, robots do not benefit from the collaborative map if the server provides no feedback in a computationally tractable and bandwidth-efficient manner.
Motivated by this challenge, this paper proposes a novel collaborative mapping framework to enable accurate global mapping among robots and server.
In particular, structural differences between robot and server graphs are exploited at different spatial scales using graph spectral analysis to generate necessary constraints for the individual robot pose graphs.
The proposed approach is thoroughly analyzed and validated using several real-world multi-robot field deployments where we show improvements in the onboard system up to 90%. [ICRA22] Collaborative Robot Mapping using Spectral Graph Analysis](https://i.ytimg.com/vi/ykSa2_J0clw/mqdefault.jpg)

