[1] Wang Dongsheng, Wang Yan, Zhou Ying, Jiang Guoping, et al. Sensor fusion for heading angle estimationbased on random forest algorithm [J]. Journal of Southeast University (English Edition), 2021, 37 (2): 192-198. [doi:10.3969/j.issn.1003-7985.2021.02.009]
Copy
Sensor fusion for heading angle estimationbased on random forest algorithm(
)
基于随机森林算法的传感器融合航向角估计
)Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]
- Volumn:
- 37
- Issue:
- 2021 2
- Page:
- 192-198
- Research Field:
- Automation
- Publishing date:
- 2021-06-20
Info
- Title:
- Sensor fusion for heading angle estimationbased on random forest algorithm
- 基于随机森林算法的传感器融合航向角估计
- Author(s):
- Wang Dongsheng; Wang Yan; Zhou Ying; Jiang Guoping
- School of Automation, Nanjing University of Posts and Telecommunications, Nanjing 210023, China
- PACS:
- TP212.9
- DOI:
- 10.3969/j.issn.1003-7985.2021.02.009
- Abstract:
- To improve the accuracy of the calculation of a heading angle under magnetic interference, magnetometers and inertial measurement units(IMUs)were fused. The observation value of the heading angle was deduced on the basis of the modeling of the magnetometer error and the analysis of the relation of the magnetometer triaxial output and the distribution characteristics of the magnetic field at two adjacent time periods. Meanwhile, the gyro state and angular velocity increment were used as the basis of the IMU to calculate the prediction value of the heading angle. With the changes in the heading angle and environmental interference, a random forest(RF)algorithm was used to iteratively calculate the weights to fuse the observation value of the heading angle based on the magnetometer and the prediction value of the heading angle based on the IMU. The results show that relative to the common sensor fusion method, the proposed sensor fusion method based on the RF algorithm achieved an approximate 60% improvement in heading angle accuracy. Hence, the proposed method can effectively improve the accuracy of the heading angle under magnetic interference by using an RF algorithm to calculate the output weights of the magnetometer and IMU.
- 为了提高磁干扰环境下的航向角计算精度, 将磁力计和惯性测量单元进行融合计算. 在构建磁力计误差模型和分析磁力计三轴输出与相邻两时刻磁场分布特征关系的基础上, 推导出航向角观测值. 同时, 采用陀螺状态和角速度增量作为惯性测量单元计算依据, 计算出航向角的预测值. 随着航向角和环境干扰的变化, 使用随机森林算法持续迭代计算权重, 将基于磁力计的航向角观测值和基于惯性测量单元的航向角预测值进行融合计算. 结果表明, 在磁干扰环境下, 相比于普通的传感器融合方法, 基于随机森林的传感器融合方法的航向角精度可提高约60%. 通过随机森林算法计算合适的磁力计和惯性测量单元的输出权重, 可有效提高磁干扰环境下的航向角计算精度.
References:
[1] Patonis P, Patias P, Tziavos I, et al. A fusion approach for combining low-cost IMU/magnetometer outputs for use in applications on mobile devices[J]. Sensors, 2017, 18(8):2616-2632. DOI: 10. 3390/s18082616.
[2] Cong L, Li E C, Qin H L, et al. A performance improvement method for low-cost land vehicle GPS/MEMS-INS attitude determination[J].Sensors(Basel, Switzerland), 2015, 15(3): 5722-5746. DOI:10.3390/s150305722.
[3] Hellmers H, Kasmi Z, Norrdine A, et al. Accurate 3D positioning for a mobile platform in non-line-of-sight scenarios based on IMU/magnetometer sensor fusion[J]. Sensors, 2018, 18(1): 126-144. DOI:10. 3390/s18010126.
[4] Zhai Y J, Zhao H L, Zhao M. Design of electric patrol UAVs based on a dual antenna system[J]. Energies, 2018, 11(4): 866-873. DOI:10.3390/en11040866.
[5] Ambati P R, Padhi R. Robust auto-landing of fixed-wing UAVs using neuro-adaptive design[J]. Control Engineering Practice, 2017, 60: 218-232. DOI:10.1016/j.conengprac.2016.03.017.
[6] Rosario M, Khamis H, Ngo P, et al. Computationally efficient adaptive error-state Kalman filter for attitude estimation[J]. IEEE Sensors Journal, 2018, 18(22): 9332-9342. DIO 10.1109/jsen.2018.2864989.
[7] Yin G, Zhang L. Magnetic heading compensation approach based on magnetic interferential signal inversion[J]. Sensors and Actuators A: Physical, 2018, 275:1-10. DOI: 10.1016/j.sna.2018.03.043.
[8] Wang Q, Yin J, Noureldin A. Research on an improved approach for foot-mounted inertial/magnetometer pedestrian-positioning based on the adaptive gradient descent algorithm[J]. Sensors, 2018, 18(12):4105-4122. DOI:10.3390/s18124105.
[9] Xing H F, Chen Z Y, Yang H T, et al. Self-alignment MEMS IMU approach based on the rotation modulation technique on a swing base[J]. Sensors, 2018, 18(4): 1178-1199. DOI: 10.3390/s18041178.
[10] Bao G Z, Wickenbrock A, Rochester S, et al. Suppression of the nonlinear Zeeman effect and heading error in earth-field-range alkali-vapor magnetometers[J]. Physical Review Letters, 2018, 120(3): 033202. DOI:10.1103/PhysRevLett.120.033202.
[11] Li G Z, Zhao S, Zhu R. Wearable anemometer with multi-sensing of wind absolute orientation, wind speed, attitude, and heading[J]. IEEE Sensors Journal, 2019, 19(1):297-303. DOI 10.1109/JSEN.2018.2874809.
[12] Song X, Li X, Tang W C, et al. A fusion strategy for reliable vehicle positioning utilizing RFID and in-vehicle sensors[J]. Information Fusion, 2016, 31(31): 76-86. DOI 10.1016/j.inffus.2016.01.003.
[13] Rantanen J, Ruotsalainen L, Kirkkojaakkola M, et al. Height measurement in seamless indoor/outdoor infrastructure-free navigation[J]. IEEE Transactions on Instrumentation and Measuremen, 2019, 68(4): 1199-1209.DOI 10.1109/TIM.2018.2863978.
[14] Xu Q, Li X, Li B. A reliable hybrid positioning methodology for land vehicles using low-cost sensors[J]. IEEE Transactions on Intelligent Transportation System, 2016, 17(3):834-847. DOI:10.1109/TITS.2015.2487518.
[15] Wu J, Zhou Z, Fourati H, et al. A super fast attitude determination algorithm for consumer-level accelerometer and magnetometer[J]. IEEE Transactions on Consumer Electronics, 2018, 64(3): 375-381. DOI 10.1109/TCE.2018.2859625.
[16] Li X, Chen W, Chan C. A reliable multisensor fusion strategy for land vehicle positioning using low-cost sensors[J]. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering, 2014, 228(12): 1375-1397. DOI 10.1177/0954407014533518.
[17] Vochin M, Vulpe A, Boicescu L, et al. An intelligent low-power displaying system with integrated emergency alerting capability[J]. Sensors, 2019, 19(3): 666. DOI 10.3390/s19030666.
[18] Qin H L, Cong L, Sun X L. Accuracy improvement of GPS/MEMS-INS integrated navigation system during GPS signal outage for land vehicle navigation[J]. Journal of Systems Engineering and Electronics, 2012, 23(2): 256-264. DOI 10.1109/JSEE.2012.00033.
[19] Jiang C, Zhang S B, Zhang Q Z. Adaptive estimation of multiple fading factors for GPS/INS integrated navigation systems[J]. Sensors, 2017, 17(6): 1254-1271. DOI 10.3390/s17061254.
[20] Cho S Y, Kim B D. Adaptive IIR/FIR fusion filter and its application to the INS/GPS integrated system[J]. Automatica, 2008, 44(8): 2040-2047. DOI 10.1016/j.automatica.2007.11.009.
[21] Pasku V, Angelis A D, Angelis G D, et al. Magnetic field-based positioning systems[J]. IEEE Communications Surveys and Tutorials, 2017, 19(3):2003-2017. DOI 10.1109/COMST.2017.2684087.
Memo
- Memo:
-
Biography: Wang Dongsheng(1983—), male, doctor, associate professor, wangdongsheng@njupt.edu.cn.
Foundation item: The National Natural Science Foundation of China(No. 51708299).
Citation: Wang Dongsheng, Wang Yan, Zhou Ying, et al. Sensor fusion for heading angle estimation based on random forest algorithm[J].Journal of Southeast University(English Edition), 2021, 37(2):192-198.DOI:10.3969/j.issn.1003-7985.2021.02.009.