Developing an Algorithm for 3D Map Construction Using Multi-robots
Doaa Mahmoud Abd El-Latif;
Abstract
Abstract
The idea of making a team of mobile robots perform a collaborative task hasnumerous benefits in many applications, especially in search and rescue missionsand fire fighting.
In this operation scenario a dense three dimensional map of the operation environmentwill be of great use, but usually it is either not present or it has been changedbecause of the fire or the collapses in the building.
This research addresses the problem of three dimension map construction using ateam of cooperative mobile robots each equipped with a visual sensor. A frameworkfor a collaborative map construction system is proposed along with a comprehensiveoverview of the state-of-art visual simultaneous localization and mapping algorithms.Depending only on the vision sensor to perform the complex task of localizationand mapping introduces many challenges in the proposed algorithm because usuallythe data provided by the sensors are noisy and sometimes they interfere with the mapupdating process resulting in false matches. The use of a team of robots also introducesmany challenges such as maintaining a coherent team behaviour, communication betweenteam members, complex tasks decomposition, subtasks assignment and aligning
and merging the partial maps constructed by individual robots into one coherent mapwhich is the focus of this study.
The research problem was divided into two parts: first building three dimensionalmaps using the observations of a single mobile robot applied many times on differentparts of the environment, second aligning and merging the m maps constructed byindividual robots with different views into one global consistent map.
The map building algorithm was divided into three main parts: registration, loopclosure and global optimization. In registration two successive observations of a singlerobot were aligned together. This resulted in an erroneous map due to the accumulationof small errors in the registration algorithm and errors in the sensed data causing the
resulting map to drift over time. These errors are detected when the robot visits alocation that has already been mapped before. The loop is closed and the drift iscalculated. Finally global optimization is applied and the drift is corrected along thewhole path covered so far.
The aligning and merging algorithm takes the m maps produced from the mappingalgorithm and work in pairs aligning and merging them together using the robotsstarting positions as an initial guess.
The proposed system was evaluated on standard datasets of indoor environments.
The evaluation showed that the absolute relative pose error between the estimatedrobot poses could be reduced to 0.01 meters and 0.56 degrees. Furthermore the resultswere compared with other state-of-art algorithms showing the strengths and weaknessesof the proposed system.
The idea of making a team of mobile robots perform a collaborative task hasnumerous benefits in many applications, especially in search and rescue missionsand fire fighting.
In this operation scenario a dense three dimensional map of the operation environmentwill be of great use, but usually it is either not present or it has been changedbecause of the fire or the collapses in the building.
This research addresses the problem of three dimension map construction using ateam of cooperative mobile robots each equipped with a visual sensor. A frameworkfor a collaborative map construction system is proposed along with a comprehensiveoverview of the state-of-art visual simultaneous localization and mapping algorithms.Depending only on the vision sensor to perform the complex task of localizationand mapping introduces many challenges in the proposed algorithm because usuallythe data provided by the sensors are noisy and sometimes they interfere with the mapupdating process resulting in false matches. The use of a team of robots also introducesmany challenges such as maintaining a coherent team behaviour, communication betweenteam members, complex tasks decomposition, subtasks assignment and aligning
and merging the partial maps constructed by individual robots into one coherent mapwhich is the focus of this study.
The research problem was divided into two parts: first building three dimensionalmaps using the observations of a single mobile robot applied many times on differentparts of the environment, second aligning and merging the m maps constructed byindividual robots with different views into one global consistent map.
The map building algorithm was divided into three main parts: registration, loopclosure and global optimization. In registration two successive observations of a singlerobot were aligned together. This resulted in an erroneous map due to the accumulationof small errors in the registration algorithm and errors in the sensed data causing the
resulting map to drift over time. These errors are detected when the robot visits alocation that has already been mapped before. The loop is closed and the drift iscalculated. Finally global optimization is applied and the drift is corrected along thewhole path covered so far.
The aligning and merging algorithm takes the m maps produced from the mappingalgorithm and work in pairs aligning and merging them together using the robotsstarting positions as an initial guess.
The proposed system was evaluated on standard datasets of indoor environments.
The evaluation showed that the absolute relative pose error between the estimatedrobot poses could be reduced to 0.01 meters and 0.56 degrees. Furthermore the resultswere compared with other state-of-art algorithms showing the strengths and weaknessesof the proposed system.
Other data
| Title | Developing an Algorithm for 3D Map Construction Using Multi-robots | Other Titles | تطويرخوارزم مبنى على التبصيرلبناء خرائط ثلاثيه الابعاد باستخدام روبوتات متعدده | Authors | Doaa Mahmoud Abd El-Latif | Issue Date | 2015 |
Recommend this item
Similar Items from Core Recommender Database
Items in Ain Shams Scholar are protected by copyright, with all rights reserved, unless otherwise indicated.