An Improved Transformed Unscented FastSLAM With Adaptive Genetic Resampling

Fast simultaneous localization and mapping (FastSLAM) is a well-known study for robot navigation. To enhance the performance of FastSLAM, an improved importance sampling is proposed in this paper based on the transformed unscented Kalman filter. The improvement is mainly composed of a novel fuzzy noise estimator, which can adjust the state and observation noises online according to the residual and related covariance, and thus mitigating the defects caused by model inaccuracy. In general, the FastSLAM algorithm suffers from the impoverishment problem since it is essentially a particle filter. Inspired by genetic optimization, an adaptive genetic resampling is proposed to substitute the conventional resampling step to overcome these defects. The proposed method, referred to as the improved transformed unscented FastSLAM, is compared with the unscented FastSLAM and the transformed unscented FastSLAM. The superiorities of the proposed method are verified by simulation and experiment under benchmark environments.

[1]  Z. Kurt-Yavuz,et al.  A comparison of EKF, UKF, FastSLAM2.0, and UKF-based FastSLAM algorithms , 2012, 2012 IEEE 16th International Conference on Intelligent Engineering Systems (INES).

[2]  Nando de Freitas,et al.  Rao-Blackwellised Particle Filtering for Dynamic Bayesian Networks , 2000, UAI.

[3]  Y. Zhong,et al.  Adaptive unscented Kalman filter based on maximum posterior and random weighting , 2017 .

[4]  Taizhi Lv,et al.  An improved FastSLAM 2.0 algorithm based on FC&ASD-PSO , 2016, Robotica.

[5]  Dipten Maiti,et al.  Efficiency and Cost Optimized Design of an Induction Motor Using Genetic Algorithm , 2017, IEEE Transactions on Industrial Electronics.

[6]  Wan Kyun Chung,et al.  Unscented FastSLAM: A Robust and Efficient Solution to the SLAM Problem , 2008, IEEE Transactions on Robotics.

[7]  Alireza Fathi,et al.  Identification of an Autonomous Underwater Vehicle Hydrodynamic Model Using the Extended, Cubature, and Transformed Unscented Kalman Filter , 2018, IEEE Journal of Oceanic Engineering.

[8]  An Li,et al.  Transformed Unscented Kalman Filter , 2013, IEEE Transactions on Automatic Control.

[9]  Mohammad Teshnehlab,et al.  A Square Root Unscented FastSLAM With Improved Proposal Distribution and Resampling , 2014, IEEE Transactions on Industrial Electronics.

[10]  C. W. Chan,et al.  Performance evaluation of UKF-based nonlinear filtering , 2006, Autom..

[11]  S. Haykin,et al.  Cubature Kalman Filters , 2009, IEEE Transactions on Automatic Control.

[12]  Alireza Mohammad Shahri,et al.  GA-inspired particle filter for mitigating severe sample impoverishment , 2016, 2016 4th International Conference on Control, Instrumentation, and Automation (ICCIA).

[13]  David W. Murray,et al.  An O(N²) Square Root Unscented Kalman Filter for Visual Simultaneous Localization and Mapping , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Yu Song,et al.  Square-root Cubature FastSLAM algorithm for mobile robot simultaneous localization and mapping , 2012, 2012 IEEE International Conference on Mechatronics and Automation.

[15]  Shen Yin,et al.  Intelligent Particle Filter and Its Application to Fault Detection of Nonlinear System , 2015, IEEE Transactions on Industrial Electronics.

[16]  Dan Liu,et al.  A Strong Tracking Square Root Central Difference FastSLAM for Unmanned Intelligent Vehicle With Adaptive Partial Systematic Resampling , 2016, IEEE Transactions on Intelligent Transportation Systems.

[17]  Chenglin Wen,et al.  Carrier Tracking Estimation Analysis by Using the Extended Strong Tracking Filtering , 2017, IEEE Transactions on Industrial Electronics.

[18]  Petar M. Djuric,et al.  Resampling Methods for Particle Filtering: Classification, implementation, and strategies , 2015, IEEE Signal Processing Magazine.

[19]  Ramazan Havangi.  Intelligent FastSLAM: An Intelligent Factorized Solution to Simultaneous Localization and Mapping , 2017, Int. J. Humanoid Robotics.

[20]  Sebastian Thrun,et al.  FastSLAM: a factored solution to the simultaneous localization and mapping problem , 2002, AAAI/IAAI.

[21]  Yu Gong,et al.  An improved resampling approach for particle filters in tracking , 2017, 2017 22nd International Conference on Digital Signal Processing (DSP).