Conference Paper

Evolutionary particle filter: Re-sampling from the genetic algorithm perspective

ARC Centre of Excellence for Autonomous Syst., Univ. of Technol., Sydney, NSW, Australia
DOI: 10.1109/IROS.2005.1545119 Conference: Intelligent Robots and Systems, 2005. (IROS 2005). 2005 IEEE/RSJ International Conference on
Source: IEEE Xplore

ABSTRACT The sample impoverishment problem in particle filters is investigated from the perspective of genetic algorithms. The contribution of this paper is in the proposal of a hybrid technique to mitigate sample impoverishment such that the number of particles required and hence the computation complexities are reduced. Studies are conducted through the use of Chebyshev inequality for the number of particles required. The relationship between the number of particles and the time for impoverishment is examined by considering the takeover phenomena as found in genetic algorithms. It is revealed that the sample impoverishment problem is caused by the resampling scheme in implementing the particle filter with a finite number of particles. The use of uniform or roulette-wheel sampling also contributes to the problem. Crossover operators from genetic algorithms are adopted to tackle the finite particle problem by re-defining or re-supplying impoverished particles during filter iterations. Effectiveness of the proposed approach is demonstrated by simulations for a monobot simultaneous localization and mapping application.

Download full-text


Available from: Gu Fang, Aug 28, 2015
  • Source
    • "Table II. Categories of primary PDO approaches to review PDO tool Typical PDO property Primary references Kernel smoothing Blind [41] [42] [43] [44] [45] [48] Data-driven method MCMC Sighted [16] [25] [33] [37] [40] [50] [51] [52] Mean-shift Sighted [33] [53] [54] [55] [56] AI algorithms (Evolution and population) GA Blind [57] [58] [59] [60] [71] PSO Sighted [63] [64] [65] [66] [91] ACO Sighted [67] [68] [69] [70] ML techniques Clustering Blind [53] [77] [78] [79] [80] [81] [82] [83] Merging/splitting Blind [36] [39] [76] Others scatter search process [61] [72], support vector machines & support vector data description [29] "
    [Show abstract] [Hide abstract]
    ABSTRACT: During the last two decades there has been a growing interest in Particle Filtering (PF). However, PF suffers from two long-standing problems that are referred to as sample degeneracy and impoverishment. We are investigating methods that are particularly efficient at Particle Distribution Optimization (PDO) to fight sample degeneracy and impoverishment, with an emphasis on intelligence choices. These methods benefit from such methods as Markov Chain Monte Carlo methods, Mean-shift algorithms, artificial intelligence algorithms (e.g., Particle Swarm Optimization, Genetic Algorithm and Ant Colony Optimization), machine learning approaches (e.g., clustering, splitting and merging) and their hybrids, forming a coherent standpoint to enhance the particle filter. The working mechanism, interrelationship, pros and cons of these approaches are provided. In addition, approaches that are effective for dealing with high-dimensionality are reviewed. While improving the filter performance in terms of accuracy, robustness and convergence, it is noted that advanced techniques employed in PF often causes additional computational requirement that will in turn sacrifice improvement obtained in real life filtering. This fact, hidden in pure simulations, deserves the attention of the users and designers of new filters.
    Expert Systems with Applications 06/2014; 41(8):3944–3954. DOI:10.1016/j.eswa.2013.12.031 · 1.97 Impact Factor
  • Source
    • "This combination outperforms other existing filters but it comes at the cost of heavy computational burden. Recent approaches are based on optimization methods to avoid the resampling stage by biasing the prior sample towards regions of the state space with high likelihood [11] [15] [17]. An approach that employs Particle Swarm Optimization (PSO) for this purpose was recently proposed [14]. "
    [Show abstract] [Hide abstract]
    ABSTRACT: ABSTRACT We propose a Particle Filter model that incorporates Parti- cle Swarm Optimization for predicting systems with multi- plicative noise. The proposed model employs a conventional multiobjective optimization approach to weight the likeli- hood and prior of the filter in order to alleviate the particle
    Genetic and Evolutionary Computation Conference, GECCO 2008, Proceedings, Atlanta, GA, USA, July 12-16, 2008; 01/2008
  • Source
    • "In order to truly approximate an arbitrary pdf, the number of samples used in a PF could approach an intractable large number. Otherwise, if insufficient samples are used (e.g., less than 10000), due to computational resource limitations, sample impoverishment problems [22] may render the PF impracticable. On the other hand, the EKF represents the pdf by parameterizing the mean and variance and the GSF contains a small multiple of these parameters. "
    [Show abstract] [Hide abstract]
    ABSTRACT: A Gaussian sum filter (GSF) is proposed in this paper on simultaneous localization and mapping (SLAM) for mobile robot navigation. In particular, the SLAM problem is tackled here for cases when only bearing measurements are available. Within the stochastic mapping framework using an extended Kalman filter (EKF), a Gaussian probability density function (pdf) is assumed to describe the range-and-bearing sensor noise. In the case of a bearing-only sensor, a sum of weighted Gaussians is used to represent the non-Gaussian robot-landmark range uncertainty, resulting in a bank of EKFs for estimation of the robot and landmark locations. In our approach, the Gaussian parameters are designed on the basis of minimizing the representation error. The computational complexity of the GSF is reduced by applying the sequential probability ratio test (SPRT) to remove under-performing EKFs. Extensive experimental results are included to demonstrate the effectiveness and efficiency of the proposed techniques.
Show more