[robotics-worldwide] [software] Code Release: DSLAM: Data-Efficient Decentralized Visual SLAM

Davide Scaramuzza scaramuzza.davide at gmail.com
Tue Apr 24 10:52:50 PDT 2018


Dear colleagues,

we are happy to release DSLAM, the code of our ICRA18 paper 
“Data-Efficient Decentralized Visual SLAM”: 
https://urldefense.proofpoint.com/v2/url?u=https-3A__github.com_uzh-2Drpg_dslam-5Fopen&d=DwIDaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rSs8MCeFamFEPafDTOhgTfYI&m=nzp67tJdGBkXn3jcKCqj8bu6cWOs6e4RpwPTvDUz9uY&s=Xdv42jfTQv-o7ULdPYibtEc07fo35_gg_lw5hwcTc8w&e=

Decentralized visual simultaneous localization and mapping (SLAM) is a 
powerful tool for multi-robot applications in environments where 
absolute positioning is not available. Being visual, it relies on cheap, 
lightweight and versatile cameras, and, being decentralized, it does not 
rely on communication to a central entity. In this work, we integrate 
state-of-the-art decentralized SLAM components into a new, complete 
decentralized visual SLAM system, DSLAM. To allow for data association 
and optimization, existing decentralized visual SLAM systems exchange 
the full map data among all robots, incurring large data transfers at a 
complexity that scales quadratically with the robot count. In contrast, 
DSLAM performs efficient data association in two stages: first, a 
compact full-image descriptor is deterministically sent to only one 
robot. Then, only if the first stage succeeded, the data required for 
relative pose estimation is sent, again to only one robot. Thus, data 
association scales linearly with the robot count and uses highly compact 
place representations. For optimization, a state-of-the-art 
decentralized pose-graph optimization method is used. It exchanges a 
minimum amount of data which is linear with trajectory overlap. We 
characterize this system and identify bottlenecks in its components. The 
system is evaluated on publicly available datasets.

The code contains C++ and Matlab code that were used for the 
decentralized SLAM simulation and is released under the GPL-3.0 license. 
Detailed instructions to reproduce the results in the paper are provided 
in the README.md .

This project will also be presented at this year's IEEE International 
Conference on Robotics and Automation (ICRA18), in Brisbane.

Reference:
Titus Cieslewski, Siddharth Choudhary, Davide Scaramuzza
Data-Efficient Decentralized Visual SLAM
IEEE International Conference on Robotics and Automation (ICRA), 2018.

PDF: https://urldefense.proofpoint.com/v2/url?u=http-3A__rpg.ifi.uzh.ch_docs_ICRA18-5FCieslewski.pdf&d=DwIDaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rSs8MCeFamFEPafDTOhgTfYI&m=nzp67tJdGBkXn3jcKCqj8bu6cWOs6e4RpwPTvDUz9uY&s=v6v1F64eAHH8l7vSyKGMxxyzgvBDemVXvzbP-AOuWgM&e=
ICRA Video Pitch: https://urldefense.proofpoint.com/v2/url?u=https-3A__youtu.be_zEBfCA5tVOk&d=DwIDaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rSs8MCeFamFEPafDTOhgTfYI&m=nzp67tJdGBkXn3jcKCqj8bu6cWOs6e4RpwPTvDUz9uY&s=PnppUc36epFW5BMMUfwtrPaJntI-yo5kZjAtw-b0TF4&e=
Presentation: https://urldefense.proofpoint.com/v2/url?u=http-3A__rpg.ifi.uzh.ch_docs_ICRA18-5FCieslewski.pptx&d=DwIDaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rSs8MCeFamFEPafDTOhgTfYI&m=nzp67tJdGBkXn3jcKCqj8bu6cWOs6e4RpwPTvDUz9uY&s=X9IxEkw0vxoxDh45MfiieIdgAjFpphQM6T7tBTSXuv4&e=
Code and Data: https://urldefense.proofpoint.com/v2/url?u=https-3A__github.com_uzh-2Drpg_dslam-5Fopen&d=DwIDaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rSs8MCeFamFEPafDTOhgTfYI&m=nzp67tJdGBkXn3jcKCqj8bu6cWOs6e4RpwPTvDUz9uY&s=Xdv42jfTQv-o7ULdPYibtEc07fo35_gg_lw5hwcTc8w&e=

The authors: Titus Cieslewski, Siddharth Choudhary, Davide Scaramuzza

-- 
___________________________________

Prof. Dr. Davide Scaramuzza
Director of the Robotics and Perception Group: 
https://urldefense.proofpoint.com/v2/url?u=http-3A__rpg.ifi.uzh.ch_people-5Fscaramuzza.html&d=DwIDaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rSs8MCeFamFEPafDTOhgTfYI&m=nzp67tJdGBkXn3jcKCqj8bu6cWOs6e4RpwPTvDUz9uY&s=FtLT3kSXG4G2SGpG1gb6kcTRiNAth7ByPog4tSXmu7k&e=
Inst. of Informatics, University of Zurich,
Inst. of Neuroinformatics, University of Zurich and ETH Zurich
Andreasstrasse 15, AND 2.10, Zurich, Switzerland
Office: +41 44 635 24 09
YouTube Channel: https://urldefense.proofpoint.com/v2/url?u=https-3A__www.youtube.com_ailabRPG_videos&d=DwIDaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rSs8MCeFamFEPafDTOhgTfYI&m=nzp67tJdGBkXn3jcKCqj8bu6cWOs6e4RpwPTvDUz9uY&s=venSpC4TaVfsPHJjbdhN0d4hx5pcfiT1DB8C_T6gtjk&e=
___________________________________


More information about the robotics-worldwide mailing list