An Improved FastSLAM Framework Based on Particle Swarm Optimization and Unscented Particle Filter ⋆

نویسندگان

  • Dongbo LIU
  • Guorong LIU
  • Miaohua YU
چکیده

FastSLAM is a framework which solves the problem of simultaneous localization and mapping using a Rao-Blackwellized particle filter. Conventional FastSLAM is known to degenerate over time in terms of accuracy due to the particle depletion in resampling phase. To solve this problem, a FastSLAM method based on particle swarm optimization and unscented particle filter is proposed. The number of particles is seriously reduced because of the particle filter based on the particle swarm optimization for pose estimation; and the landmarks updated through Unscented Kalman filter to improve map estimation accuracy. The method can enhance the SLAM precision effectively, and reduce the particle number and the computational time complexity. The simulation experiment results prove its effectiveness and feasibility.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

A Neuro-Fuzzy Multi Swarm FastSLAM Framework

FastSLAM is a framework for simultaneous localization using a Rao-Blackwellized particle filter. In FastSLAM, particle filter is used for the mobile robot pose (position and orientation) estimation, and an Extended Kalman Filter (EKF) is used for the feature location’s estimation. However, FastSLAM degenerates over time. This degeneracy is due to the fact that a particle set estimating the pose...

متن کامل

Unscented Auxiliary Particle Filter Implementation of the Cardinalized Probability Hypothesis Density Filters

The probability hypothesis density (PHD) filter suffers from lack of precise estimation of the expected number of targets. The Cardinalized PHD (CPHD) recursion, as a generalization of the PHD recursion, remedies this flaw and simultaneously propagates the intensity function and the posterior cardinality distribution. While there are a few new approaches to enhance the Sequential Monte Carlo (S...

متن کامل

A New Modified Particle Filter With Application in Target Tracking

The particle filter (PF) is a novel technique that has sufficiently good estimation results for the nonlinear/non-Gaussian systems. However, PF is inconsistent that caused mainly by loss of particle diversity in resampling step and unknown a priori knowledge of the noise statistics. This paper introduces a new modified particle filter called adaptive unscented particle filter (AUPF) to overcome th...

متن کامل

Improved Binary Particle Swarm Optimization Based TNEP Considering Network Losses, Voltage Level, and Uncertainty in Demand

Transmission network expansion planning (TNEP) is an important component of power system planning. Itdetermines the characteristics and performance of the future electric power network and influences the powersystem operation directly. Different methods have been proposed for the solution of the static transmissionnetwork expansion planning (STNEP) problem till now. But in all of them, STNEP pr...

متن کامل

An improved FastSLAM framework using soft computing

FastSLAM is a framework for simultaneous localization and mapping (SLAM) using a Rao-Blackwellized particle filter. However, FastSLAM degenerates over time. This degeneracy is due to the fact that a particle set estimating the pose of the robot loses its diversity. One of the main reasons for losing particle diversity in FastSLAM is sample impoverishment. In this case, most of the particle weig...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2012