Adaptive EKF Based on HMM Recognizer for Attitude Estimation Using MEMS MARG Sensors

This paper addresses the intractable problem of attaining precise attitude estimation efficiently using MEMS MARG (magnetic, angular rate, and gravity) sensors for 3-D motion tracking, which is called attitude and heading reference system (AHRS). The performance of AHRS is adversely affected by sensor noise and measurement disturbances. To overcome this problem, we propose a novel adaptive extended Kalman filter (AEKF) in this paper, including a multiplicative extended Kalman filter (MEKF) and a hidden Markov Model (HMM) recognizer. MEKF is built on sensor noise model. An HMM recognizer is developed to identify the measurement disturbance caused by motion or environmental interference and then to adjust the noise covariance of MEKF adaptively. The proposed AEKF was assessed with a high-precision test platform by using a high-caliber commercial AHRS. Experimental results indicate that the proposed method achieves a higher level of stability and accuracy in comparison to other attitude estimators, especially in dynamic tests, which demonstrates the availability of 3-D motion tracking.

[1]  Xiaoli Meng,et al.  Quaternion-Based Kalman Filter With Vector Selection for Accurate Orientation Tracking , 2012, IEEE Transactions on Instrumentation and Measurement.

[2]  Huosheng Hu,et al.  Inertial motion tracking of human arm movements in stroke rehabilitation , 2005, IEEE International Conference Mechatronics and Automation, 2005.

[3]  Christian Kohlschein.  An introduction to Hidden Markov Models , 2007 .

[4]  Ya Tian,et al.  An Adaptive-Gain Complementary Filter for Real-Time Human Motion Tracking With MARG Sensors in Free-Living Environments , 2013, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[5]  Mark J. F. Gales,et al.  Maximum likelihood linear transformations for HMM-based speech recognition , 1998, Comput. Speech Lang..

[6]  Alexandra Pfister,et al.  Comparative abilities of Microsoft Kinect and Vicon 3D motion capture for gait analysis , 2014, Journal of medical engineering & technology.

[7]  Peter H Veltink,et al.  Accelerometer and rate gyroscope measurement of kinematics: an inexpensive alternative to optical motion analysis systems. , 2002, Journal of biomechanics.

[8]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[9]  Felipe Espinosa,et al.  UAV Attitude Estimation Using Unscented Kalman Filter and TRIAD , 2012, IEEE Transactions on Industrial Electronics.

[10]  K. C. Daly,et al.  Star-Sensor-Based Satellite Attitude/Attitude Rate Estimator , 1985 .

[11]  John L. Crassidis,et al.  Survey of nonlinear attitude estimation methods , 2007 .

[12]  Oliver J. Woodman,et al.  An introduction to inertial navigation , 2007 .

[13]  Hyun Jin Kim,et al.  A Human Motion Tracking Algorithm Using Adaptive EKF Based on Markov Chain , 2016, IEEE Sensors Journal.

[14]  S. F. Schmidt,et al.  The Kalman filter - Its recognition and development for aerospace applications , 1981 .

[15]  Michael I. Jordan,et al.  Factorial Hidden Markov Models , 1995, Machine Learning.

[16]  Thomas Beth,et al.  Characteristics in human motion - from acquisition to analysis , 2003 .

[17]  Huosheng Hu,et al.  Integration of Vision and Inertial Sensors for 3D Arm Motion Tracking in Home-based Rehabilitation , 2007, Int. J. Robotics Res..

[18]  Saeed V. Vaseghi,et al.  Advanced Digital Signal Processing and Noise Reduction , 2006 .

[19]  Michael Zyda,et al.  Orientation tracking for humans and robots using inertial sensors , 1999, Proceedings 1999 IEEE International Symposium on Computational Intelligence in Robotics and Automation. CIRA'99 (Cat. No.99EX375).

[20]  Robert E. Mahony,et al.  Nonlinear Complementary Filters on the Special Orthogonal Group , 2008, IEEE Transactions on Automatic Control.

[21]  J. Stuelpnagel.  On the Parametrization of the Three-Dimensional Rotation Group , 1964 .

[22]  António H. J. Moreira,et al.  Real-time hand tracking for rehabilitation and character animation , 2014, 2014 IEEE 3nd International Conference on Serious Games and Applications for Health (SeGAH).

[23]  Panos Marantos,et al.  UAV State Estimation Using Adaptive Complementary Filters , 2016, IEEE Transactions on Control Systems Technology.

[24]  Aria Alasty,et al.  Human Arm Motion Tracking by Orientation-Based Fusion of Inertial Sensors and Kinect Using Unscented Kalman Filter. , 2016, Journal of biomechanical engineering.

[25]  Luca Fanucci,et al.  A Double-Stage Kalman Filter for Orientation Tracking With an Integrated Processor in 9-D IMU , 2013, IEEE Transactions on Instrumentation and Measurement.

[26]  R. Farrenkopf.  Analytic Steady-State Accuracy Solutions for Two Common Spacecraft Attitude Estimators , 1978 .

[27]  M. Shuster.  A survey of attitude representation , 1993 .

[28]  Young Soo Suh.  Orientation Estimation Using a Quaternion-Based Indirect Kalman Filter With Adaptive Estimation of External Acceleration , 2010, IEEE Transactions on Instrumentation and Measurement.

[29]  Angelo M. Sabatini,et al.  Estimating Three-Dimensional Orientation of Human Body Parts by Inertial/Magnetic Sensing , 2011, Sensors.

[30]  Yunlong Wang,et al.  An Attitude Heading and Reference System for Marine Satellite Tracking Antenna , 2017, IEEE Transactions on Industrial Electronics.

[31]  Changbin Yu,et al.  Unit-Dual-Quaternion-Based PID Control Scheme for Rigid-Body Transformation , 2011 .

[32]  L. Baum,et al.  A Maximization Technique Occurring in the Statistical Analysis of Probabilistic Functions of Markov Chains , 1970 .

[33]  Xiaoping Yun,et al.  Design, Implementation, and Experimental Results of a Quaternion-Based Kalman Filter for Human Body Motion Tracking , 2006, IEEE Trans. Robotics.

[34]  Zhaoying Zhou,et al.  A real-time articulated human motion tracking using tri-axis inertial/magnetic sensors package. , 2004, IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.

[35]  F. Markley.  Attitude Error Representations for Kalman Filtering , 2003 .

[36]  John L. Crassidis,et al.  Fundamentals of Spacecraft Attitude Determination and Control , 2014 .

[37]  Roland Siegwart,et al.  Onboard IMU and monocular vision based control for MAVs in unknown in- and outdoor environments , 2011, 2011 IEEE International Conference on Robotics and Automation.

[38]  Andrea Vitali,et al.  Development of a wireless low-power multi-sensor network for motion tracking applications , 2013, 2013 IEEE International Conference on Body Sensor Networks.

[39]  Sebastian Madgwick,et al.  Estimation of IMU and MARG orientation using a gradient descent algorithm , 2011, 2011 IEEE International Conference on Rehabilitation Robotics.

[40]  Robert B. McGhee,et al.  An extended Kalman filter for quaternion-based orientation estimation using MARG sensors , 2001, Proceedings 2001 IEEE/RSJ International Conference on Intelligent Robots and Systems. Expanding the Societal Role of Robotics in the the Next Millennium (Cat. No.01CH37180).

[41]  Sean R. Eddy,et al.  Profile hidden Markov models , 1998, Bioinform..

[42]  Yu-Liang Hsu,et al.  A Wearable Inertial Pedestrian Navigation System With Quaternion-Based Extended Kalman Filter for Pedestrian Localization , 2017, IEEE Sensors Journal.

[43]  Huosheng Hu,et al.  Human motion tracking for rehabilitation - A survey , 2008, Biomed. Signal Process. Control..

[44]  Luca De Vito,et al.  Measurements and sensors for motion tracking in motor rehabilitation , 2014, IEEE Instrumentation & Measurement Magazine.