Navigation of an autonomous mobile robot using EKF-SLAM and FastSLAM

Sąsiadek, Jurek Z.; Monjazeb, A.; Necsulescu, D.

doi:10.1109/med.2008.4602213

Cited by 23 publications

(11 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The range of the sensor was set to 50 meters. All other specifications of the vehicle and sensor were held the same as [17]. Figure 2-a, illustrates a situation in which EKF algorithm was used.…”

Section: Resultsmentioning

confidence: 99%

Autonomous navigation among large number of nearby landmarks using FastSLAM and EKF-SLAM - A comparative study

Monjazeb

Sąsiadek

Necsulescu

2011

2011 16th International Conference on Methods &Amp; Models in Automation &Amp; Robotics

Self Cite

View full text Add to dashboard Cite

This paper compares two commonly used algorithms to solve Simultaneous Localization and Mapping (SLAM) problem in order to safely navigate an outdoor autonomous robot in an unknown location and without any access to a priori map. EKF-SLAM is considered as a classical method to solve SLAM problem. This method, however, suffers from two major issues; the quadratic computational complexity and single hypothesis data association. Large number of landmarks in the environment, especially, nearby landmarks, causes extensive error accumulation when the robot is traveling along a desired path. The multi-hypothesis data association property and the linear computational complexity are essential features in FastSLAM method. Those features make this method an alternative to overcome mentioned issues. The FastSLAM algorithm uses Rao-Blackwellised particle filtering to estimate the path of the robot and EKF-SLAM method to estimate locations of landmarks. In case of FastSLAM applications, however, observation noise needs to be reconsidered if the motion measurements are noisy while the range sensor is noiseless. This study suggests optimization of a specific situation of FastSLAM algorithm in case of noise discrepancy.

show abstract

Section: Resultsmentioning

confidence: 99%

Autonomous navigation among large number of nearby landmarks using FastSLAM and EKF-SLAM - A comparative study

Monjazeb

Sąsiadek

Necsulescu

2011

2011 16th International Conference on Methods &Amp; Models in Automation &Amp; Robotics

Self Cite

View full text Add to dashboard Cite

show abstract

“…HybridSLAM remembers long term uncertainty over robot's path since main covariance matrix of the system in EKF maintains covariance between robot's pose and position of landmarks for the rest of calculation [1]. Combining EKF-SLAM and FastSLAM and representing it as HybridSLAM makes the filter to overcome some issues at which either individual filter becomes inconsistent [2].…”

Section: Unscented Hybridslammentioning

confidence: 99%

Autonomous mobile robot positioning using Unscented HybridSLAM

Monjazeb

Sąsiadek

Necsulescu

2013

2013 18th International Conference on Methods &Amp; Models in Automation &Amp; Robotics (MMAR)

Self Cite

View full text Add to dashboard Cite

This paper addresses a novel approach to Simultaneous Localization and Mapping problem called Unscented HybridSLAM. Analyzing loop closing as one of the most important aspects of SLAM is the major interest of this study. Closing a loop by an autonomous mobile robot can be tricky even in the presence of a correct data association in the process, especially, when the loop is considerably large. The main challenge is to maintain a track of all correlations among landmarks and the mobile robot using Unscented HybridSLAM. The performance of proposed algorithm is evaluated with a loop closing scenario simulation, then, the results are discussed and compared with other algorithms.

show abstract

“…It is a popular method for online SLAM, and provides a fresh new solution to the data association problem in SLAM. Experimental results and comparison between these two approaches can be found in [2,3].…”

Section: Introductionmentioning

confidence: 99%

Visual based SLAM using modified PSO

Low

Nagarajan

Yaacob

2010

2010 6th International Colloquium on Signal Processing &Amp; Its Applications

View full text Add to dashboard Cite

Simultaneous Localization and Mapping (SLAM) addresses the problem of a robot navigating and acquiring spatial models of initially unknown environments, without an absolute localization means. To solve this problem, we propose a mapping system that builds feature-based geometrical maps by applying a modified Particle Swarm Optimization (PSO) algorithm. Particles are defined as the location of individual features in the environment where the size of the swarm increases as the features are re-observed at different positions. PSO adjusts the velocity and location of particles towards a target (feature location) as the particles move around the constrained 2-dimensional search space. Finally, the particles will converge around an optimum feature location. The mobile robot is also localized with respect to this map simultaneously. It is demonstrated that accurate feature locations can be obtained using the proposed technique.

show abstract

Navigation of an autonomous mobile robot using EKF-SLAM and FastSLAM

Cited by 23 publications

References 7 publications

Autonomous navigation among large number of nearby landmarks using FastSLAM and EKF-SLAM - A comparative study

Autonomous navigation among large number of nearby landmarks using FastSLAM and EKF-SLAM - A comparative study

Autonomous mobile robot positioning using Unscented HybridSLAM

Visual based SLAM using modified PSO

Contact Info

Product

Resources

About