Windowing and random weighting-based adaptive unscented Kalman filter. (English) Zbl 1337.93091
Summary: The conventional Unscented Kalman filter (UKF) requires prior knowledge on system noise statistics. If the statistical characteristics of system noise are not known exactly, the filtering solution will be biased or even divergent. This paper presents an adaptive UKF by combining the windowing and random weighting concepts to address this problem. It extends the windowing concept from the linear Kalman filter to the nonlinear UKF for estimation of system noise statistics. Subsequently, the random weighting concept is adopted to refine the obtained windowing estimation by adjusting random weights of each window. The proposed adaptive UKF overcomes the limitation of the conventional UKF by online estimating and adjusting system noise statistics. Experimental results and comparison analysis demonstrate that the proposed adaptive UKF outperforms the conventional UKF and adaptive robust UKF under the condition without precise knowledge on system noise statistics.
MSC:
| 93E11 | Filtering in stochastic control theory |
| 93E10 | Estimation and detection in stochastic control theory |
| 93C40 | Adaptive control/observation systems |
| 93C55 | Discrete-time control/observation systems |
| 93C10 | Nonlinear systems in control theory |
References:
| [1] | JulierSJ, UhlmannJK. Unscented filtering and nonlinear estimation. Proceedings of the IEEE2004; 92(3): 401-422. |
| [2] | XiaYQ, DengZH, LiL, GengXM. A new continuous‐discrete particle filter for continuous‐discrete nonlinear systems. Information Sciences2013; 242(1): 64-75. · Zbl 1320.93083 |
| [3] | XiaYQ, LiL, MahmoudMS, YangHJ. H ∞ filtering for nonlinear singular Markovian jumping systems with interval time‐varying delays. International Journal of Systems Science2012; 43(2): 272-284. · Zbl 1259.93120 |
| [4] | ChoSY, KimBD. Adaptive IIR/FIR fusion filter and its application to the INS/GPS integrated system. Automatica2008; 44(8): 2040-2047. · Zbl 1283.93276 |
| [5] | PanQ, YangF, YeL, LiangY, ChengYM. Survey of a kind of nonlinear filter‐UKF. Control and Decision2005; 20(5): 481-489. |
| [6] | LeeDJ. Nonlinear estimation and multiple sensor fusion using unscented information filtering. IEEE Signal Processing Letters2008; 15: 861-864. |
| [7] | YanLP, XiaoB, XiaYQ, FuMY. State estimation for asynchronous multirate multisensor nonlinear dynamic systems with missing measurements. International Journal of Adaptive Control and Signal Processing2012; 26(6): 516-529. · Zbl 1263.93218 |
| [8] | JulierSJ, UhlmannJK. A new extension of the Kalman filter to nonlinear systems, In the Proceedings of AeroSense: the 11th International Symposium on Aerospace/Defense Sensing, Simulation and Controls, Orlando, Florida, 1997; 182-193. |
| [9] | WangQT, HuXL. Improved Kalman filtering algorithm for passive BD/SINS integrated navigation system based on UKF. Journal of Systems Engineering and Electronics2010; 32(2):376-379. |
| [10] | LiL, XiaYQ. Stochastic stability of the unscented Kalman filter with intermittent observations. Automatica2012; 48(5): 978-981. · Zbl 1246.93121 |
| [11] | XiongK, LiuLD, ZhangHY. Modified unscented Kalman filtering and its application in autonomous satellite navigation. Aerospace Science and Technology2009; 13(4): 238-246. |
| [12] | SongQ, HanJD. An adaptive UKF algorithm for the state and parameter estimation of a mobile robot. Acta Automatica Sinica2008; 34(1): 72-79. · Zbl 1174.93712 |
| [13] | GobboDD, NapolitanoM, FamouriP, InnocentiM. Experimental application of extended Kalman filtering for sensor validation. IEEE Transactions on Control System Technology2001; 9(2):376-380. |
| [14] | LjungL. Asymptotic behavior of the extended Kalman filter as a parameter estimator for linear systems. IEEE Transactions on Automatic Control1979; AC‐24: 36-50. · Zbl 0399.93054 |
| [15] | JulierSJ, UhlmannJK, Durrant‐WhyteHF. A new method for the nonlinear transformation of means and covariances in filters and estimators. IEEE Transactions on Automatic Control2000; 45(3):477-482. · Zbl 0973.93053 |
| [16] | TangXJ, YanJ, ZhongDD. Square‐root sigma‐point Kalman filtering for spacecraft relative navigation. Acta Astronautica2010; 66(5):704-713. |
| [17] | UhlmannJK. Simultaneous map building and localization for real time applications. Technical report, University of Oxford: Oxford, U.K., 1994. Transfer thesis. |
| [18] | SokenHE, HajiyevC. Pico satellite attitude estimation via robust unscented Kalman filter in the presence of measurement faults. ISA transactions2010; 49(3): 249-256. |
| [19] | XiongK, ZhangHY, ChanCW. Performance evaluation of UKF‐based nonlinear filtering. Automatica2006; 42(2): 261-270. · Zbl 1103.93045 |
| [20] | ChoSY, ChoiWS. Robust positioning technique in lowcost DR/GPS for land navigation. IEEE Transactions on Instrumentation and Measurement2006; 55(4): 1132-1142. |
| [21] | WangQT. The theory and application research of adaptive‐robust UKF for satellite integrated navigation system. Ph.D. Thesis, Huazhong University of Science and Technology, 2010. |
| [22] | ZhaoL, WangXX, SunM, et al. Adaptive UKF filtering algorithm based on maximum a posterior estimation and exponential weighting. Acta Automatica Sinica2010; 36(7): 1007-1019. · Zbl 1240.93337 |
| [23] | SageAP, HusaGW. Adaptive filtering with unknown prior statistics, In the Proceedings of Joint American Control Conference, Boulder, Colorado, 1969; 769-774. |
| [24] | YangYX, XuTH. An adaptive Kalman filter based on Sage windowing weights and variance components. The Journal of Navigation2003; 56(2): 231-240. |
| [25] | MohamedAH, SchwarzKP. Adaptive Kalman filtering for INS/GPS. Journal of Geodesy1999; 73(4): 193-203. · Zbl 1001.86014 |
| [26] | YangYX, WenYL. Synthetically adaptive robust filtering for satellite orbit determination. Science in China ‐ Earth Sciences2004; 47(7): 585-592. |
| [27] | YangYX, ZhangSC. Adaptive fitting for systematic errors in navigation. Journal of Geodesy2005; 79(1‐3): 43-49. · Zbl 1274.86027 |
| [28] | XuTH, JiangN, SunZZ. An improved adaptive Sage filter with applications in GEO orbit determination and GPS kinematic positioning. Science in China ‐ Physics, Mechanics & Astronomy2012; 55(5): 892-898. |
| [29] | ZhengZG. Random weighting method. Acta Mathematicae Applicatae Sinica1987; 10(2): 247-253. · Zbl 0639.62031 |
| [30] | GaoSS, ZhangZL, YangB. The random weighting estimate of quantile process. Information Sciences2004; 164(1-4): 139-146. · Zbl 1056.62061 |
| [31] | GaoSS, FengZH, ZhongYM, ShirinzadehB. Random weighting estimation of parameters in generalized Gaussian distribution. Information Sciences2008; 178(9): 2275-2281. |
| [32] | FangYX, ZhaoLC. Approximation to the distribution of LAD estimators for censored regression by random weighting method. Journal of Statistical Planning and Inference2006; 136(4): 1302-1316. · Zbl 1156.62347 |
| [33] | WuXY, YangYN, ZhaoLC. Approximation by random weighting method for M‐test in linear models. Science in China ‐ Mathematics2007; 50(1): 87-99. · Zbl 1114.62074 |
| [34] | GaoSS, ZhongYM, ShirinzadehB. Random weighting estimation for fusion of multi‐dimensional position data. Information Sciences2010; 180(24): 4999-5007. |
| [35] | GaoSS, ZhongYM, LiW. Random weighting method for multi‐sensor data fusion. IEEE Sensors Journal2011; 11(9): 1955-1961. |
| [36] | GaoSS, GaoY, ZhongYM, WeiWH. Random weighting estimation method for dynamic navigation positioning. Chinese Journal of Aeronautics2011; 24(3): 318-323. |
| [37] | GaoSS, WeiWH. A new and efficient method for random weighting estimation of kinematic model systematic error. Journal of Northwestern Polytechnical University2011; 29(6): 839-843. |
| [38] | MaybeckPS. Stochastic Models, Estimation and Control, Academic Press: New York, 1979. · Zbl 0464.93002 |
| [39] | ShiY, HanCZ. Adaptive UKF method with applications to target tracking. Acta Automatica Sinica2011; 37(6): 755-759. |
| [40] | GordonNJ, SalmondDJ, SmithAF. Novel approach to nonlinear/non‐Gaussian Bayesian state estimation. IEEE Proceedings‐F1993; 140(2): 107-113. |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
