Adaptive Neuro-Fuzzy Extended Kaiman Filtering for robot localization

Havangi, Ramazan; Nekoui, Mohammad Ali; Teshnehlab, Mohammad

doi:10.1109/epepemc.2010.5606833

Cited by 18 publications

(10 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The pose estimate is updated according to the sensory information based on the theory of Extended Kalman Filter (EKF). The non-linear kinematic model of pose estimate and the sensory measurement model are given as follows [16][17][18][19] s k+1 = f (s k , u k , w k , ψ k ),…”

Section: Pose Tracking With Odometric Error Feedbackmentioning

confidence: 99%

An efficient approach to pose tracking based on odometric error modelling for mobile robots

Yang

Cai

2014

Robotica

View full text Add to dashboard Cite

Odometric error modelling for mobile robots is the basis of pose tracking. Without bounds the odometric accumulative error decreases localisation precision after long-range movement, which is often not capable of being compensated for in real time. Therefore, an efficient approach to odometric error modelling is proposed in regard to different drive type mobile robots. This method presents a hypothesis that the motion path approximates a circular arc. The approximate functional expressions between the control input of odometry and non-systematic error as well as systematic error derived from odometric error propagation law. Further an efficient algorithm of pose tracking is proposed for mobile robots, which is able to compensate for the non-systematic and systematic error in real time. These experiments denote that the odometric error modelling reduces the accumulative error of odometry efficiently and improves the specific localisation process significantly during autonomous navigation.

show abstract

Section: Pose Tracking With Odometric Error Feedbackmentioning

confidence: 99%

An efficient approach to pose tracking based on odometric error modelling for mobile robots

Yang

Cai

2014

Robotica

View full text Add to dashboard Cite

show abstract

“…One effective solution to deal with this issue is to employ adaptive algorithms for EKF SLAM. 9,10,11,12,13 Specifically, the studies of the literature 14,15 have shown that the approach of artificial intelligence-assisted EKF for the SLAM problems is far more superior than the conventional approaches (e.g. unscented filter, square root unscented filter) and others (e.g.…”

Section: Introductionmentioning

confidence: 99%

Incorporating neuro-fuzzy with extended Kalman filter for simultaneous localization and mapping

Hung

Lin

2019

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

Extended Kalman filter is well-known as a popular solution to the simultaneous localization and mapping problem for mobile robot platforms or vehicles. In this article, the development of a neuro-fuzzy-based adaptive extended Kalman filter technique is presented. The objective is to estimate the proper values of the R matrix at each step. We design an adaptive neuro-fuzzy extended Kalman filter to minimize the difference between the actual and theoretical covariance matrices of the innovation consequence. The parameters of the adaptive neuro-fuzzy extended Kalman filter is then trained offline using a particle swarm optimization technique. With this approach, the advantages of high-dimensional search space can be exploited and more effective training can be achieved. In the experiments, the mobile robot navigation with a number of landmarks under two benchmark situations is evaluated. The results have demonstrated that the proposed adaptive neuro-fuzzy extended Kalman filter technique provides the improvement in both performance efficiency and computational cost.

show abstract

“…It occurs when likelihood lies in the tail of the proposal distribution [4]. Researchers have been trying to solve these problems in [4], [11][12][13][14][15][16]. In [16], a modi ed FastSLAM1.0 is presented by soft computing.…”

Section: Introductionmentioning

confidence: 99%

Improved FastSLAM2.0 using ANFIS and PSO

Havangi

2016

Automatika

Self Cite

View full text Add to dashboard Cite

Original scienti c paper FastSLAM2.0 is a framework for simultaneous localization of robot using a Rao-Blackwellized particle lter (RBPF). One of the problems of FastSLAM2.0 relates to the design of RBPF. The performance and quality of the estimation of RBPF depends heavily on the correct a priori knowledge of the process and measurement noise covariance matrices that are in most real-life applications unknown. On the other hand, an incorrect a priori knowledge may seriously degrade their performance. This paper presents an intelligent RBPF to solve this problem. In this method, two adaptive Neuro-Fuzzy inference systems (ANFIS) are used for tuning the process and measurement noise covariance matrices and for increasing acuuracy and consistency. In addition, we use particle swarm optimization (PSO) to optimize the performance of sampling. Experimental results demonstrate that the proposed algorithm is effective.

show abstract

Adaptive Neuro-Fuzzy Extended Kaiman Filtering for robot localization

Cited by 18 publications

References 21 publications

An efficient approach to pose tracking based on odometric error modelling for mobile robots

An efficient approach to pose tracking based on odometric error modelling for mobile robots

Incorporating neuro-fuzzy with extended Kalman filter for simultaneous localization and mapping

Improved FastSLAM2.0 using ANFIS and PSO

Contact Info

Product

Resources

About