Evolutionary computation for intelligent self-localization in multiple mobile robots based on SLAM

Authors:
Yuichiro Toda;Shintaro Suzuki;Naoyuki Kubota
Affiliations:
Graduate School of System Design, Tokyo Metropolitan University, Tokyo, Japan;Graduate School of System Design, Tokyo Metropolitan University, Tokyo, Japan;Graduate School of System Design, Tokyo Metropolitan University, Tokyo, Japan
Venue:
ICIRA'12 Proceedings of the 5th international conference on Intelligent Robotics and Applications - Volume Part I
Year:
2012

Citing 10
Cited 0

Evolutionary Computation: The Fossil Record

Evolutionary Computation: The Fossil Record
Learning Occupancy Grid Maps with Forward Sensor Models

Autonomous Robots
Effective maximum likelihood grid map withconflict evaluation filter using sonar sensors

IEEE Transactions on Robotics
Steady-state genetic algorithms for growing topological mapping and localization

PRICAI'10 Proceedings of the 11th Pacific Rim international conference on Trends in artificial intelligence
Observability-based consistent EKF estimators for multi-robot cooperative localization

Autonomous Robots
Planning for multi-robot localization

SBIA'10 Proceedings of the 20th Brazilian conference on Advances in artificial intelligence
Autonomous topological modeling of a home environment and topological localization using a sonar grid map

Autonomous Robots
Multi-robot coalition formation

IEEE Transactions on Robotics
Closing the Loop With Graphical SLAM

IEEE Transactions on Robotics
iSAM: Incremental Smoothing and Mapping

IEEE Transactions on Robotics

Quantified Score

Hi-index	0.00

Visualization

Abstract

The localization is one of the most important capabilities for mobile robots. However, other robots can be considered as unknown objects when a mobile robot performs localization, because other robots can enter the sensing range of a mobile robot. Therefore, we propose a method of intelligent self-localization using evolutionary computation for multiple mobile robots based on simultaneous localization and mapping (SLAM). First, we explain the method of SLAM using occupancy grid mapping by a single mobile robot. Next, we propose an intelligent self-localization method using multi-resolution map and evolutionary computation based on relative position of other robots in the sensing range. The experimental results show the effectiveness of the proposed method.