Time Series Forecasting of Mobile Robot Motion Sensors Using LSTM Networks

Vagale, Anete; Šteina, Luīze; Vēciņš, Valters

doi:10.2478/acss-2021-0018

Abstract

Deep neural networks are a tool for acquiring an approximation of the robot mathematical model without available information about its parameters. This paper compares the LSTM, stacked LSTM and phased LSTM architectures for time series forecasting. In this paper, motion sensor data from mobile robot driving episodes are used as the experimental data. From the experiment, the models show better results for short-term prediction, where the LSTM stacked model slightly outperforms the other two models. Finally, the predicted and actual trajectories of the robot are compared.

References

[1] J. G. De Gooijer and R. J. Hyndman, “25 years of time series forecasting,” International Journal of Forecasting, vol. 22, no. 3, pp. 443–473, 2006. https://doi.org/10.1016/j.ijforecast.2006.01.00110.1016/j.ijforecast.2006.01.001
Search in Google Scholar Back to article
[2] A. Tealab, “Time series forecasting using artificial neural networks methodologies: A systematic review,” Future Computing and Informatics Journal, vol. 3, no. 2, pp. 334–340, Dec. 2018. https://doi.org/10.1016/j.fcij.2018.10.00310.1016/j.fcij.2018.10.003
Search in Google Scholar Back to article
[3] F. Chenavier and J. L. Crowley, “Position estimation for a mobile robot using vision and odometry,” in IEEE International Conference on Robotics and Automation, Nice, France, May 1992. https://doi.org/10.1109/robot.1992.22005210.1109/ROBOT.1992.220052
Search in Google Scholar Back to article
[4] F. Azizi and N. Houshangi, “Mobile robot position determination using data from gyro and odometry,” in Canadian Conference on Electrical and Computer Engineering, vol. 2, Niagara Falls, ON, Canada, May 2004, pp. 719–722. https://doi.org/10.1109/CCECE.2004.134521510.1109/CCECE.2004.1345215
Search in Google Scholar Back to article
[5] R. Hyndman and G. Athanasopoulos, Forecasting: Principles and Practice, 3rd ed., Melbourne, Australia: OTexts, 2021.
Search in Google Scholar Back to article
[6] G. E. P. Box, G. M. Jenkins, G. C. Reinsel, and G. M. Ljung, Time Series Analysis: Forecasting and Control, 5th ed. Wiley, 2016.
Search in Google Scholar Back to article
[7] D. Mwanga, J. Ong’ala, and G. Orwa, “Modeling sugarcane yields in the Kenya sugar industry: A SARIMA model forecasting approach,” International Journal of Statistics and Applications, vol. 7, no. 6, pp. 280–288, 2017.
Search in Google Scholar Back to article
[8] Z. Wang and Y. Lou, “Hydrological time series forecast model based on wavelet de-noising and ARIMA-LSTM,” in Proceedings of 2019 IEEE 3rd Information Technology, Networking, Electronic and Automation Control Conference, (ITNEC), Chengdu, China, Mar. 2019, pp. 1697–1701. https://doi.org/10.1109/ITNEC.2019.872944110.1109/ITNEC.2019.8729441
Search in Google Scholar Back to article
[9] B. Lim and S. Zohren, “Time-series forecasting with deep learning: A survey,” Philosophical Transactions of the Royal Society A, vol. 379, Feb. 2021. https://doi.org/10.1098/rsta.2020.020910.1098/rsta.2020.020933583273
Search in Google Scholar Back to article
[10] N. K. Ahmed, A. F. Atiya, N. El Gayar, and H. El-Shishiny, “An empirical comparison of machine learning models for time series forecasting,” Econometric Reviews, vol. 29, no. 5, pp. 594–621, Sep. 2010. https://doi.org/10.1080/07474938.2010.48155610.1080/07474938.2010.481556
Search in Google Scholar Back to article
[11] C. Deb, F. Zhang, J. Yang, S. E. Lee, and K. W. Shah, “A review on time series forecasting techniques for building energy consumption,” Renewable and Sustainable Energy Reviews, vol. 74, pp. 902–924, Jul. 2017. https://doi.org/10.1016/j.rser.2017.02.08510.1016/j.rser.2017.02.085
Search in Google Scholar Back to article
[12] Z. Duan, H. Liu, X. Lv, Z. Ren, and S. Junginger, “Hybrid position forecasting method for mobile robot transportation in smart indoor environment,” in Proceedings of the 2019 4th International Conference on Big Data and Computing (ICBDC), Association for Computing Machinery, May 2019, pp. 333–338. https://doi.org/10.1145/3335484.333550810.1145/3335484.3335508
Search in Google Scholar Back to article
[13] S. Gomez-Gonzalez, S. Prokudin, B. Scholkopf, and J. Peters, “Real time trajectory prediction using deep conditional generative models,” IEEE Robotics and Automation Letters, vol. 5, no. 2, pp. 970–976, Apr. 2020. https://doi.org/10.1109/LRA.2020.296639010.1109/LRA.2020.2966390
Search in Google Scholar Back to article
[14] C. C. Aggarwal, Neural Networks and Deep Learning. Springer, 2018. https://doi.org/10.1007/978-3-319-94463-010.1007/978-3-319-94463-0
Search in Google Scholar Back to article
[15] Z. Karevan and J. A. K. Suykens, “Spatio-temporal stacked LSTM for temperature prediction in weather forecasting,” ArXiv, no. 1811.06341, Nov. 2018.
Search in Google Scholar Back to article
[16] D. Neil, M. Pfeiffer, and S.-C. Liu, “Phased LSTM: Accelerating recurrent network training for long or event-based sequences,” ArXiv, no. 1610.09513, Oct. 2016.
Search in Google Scholar Back to article
[17] F. A. Gers, N. N. Schraudolph, and J. Schmidhuber, “Learning precise timing with LSTM recurrent networks,” Journal of Machine Learning Research, vol. 3, pp. 115–143, Aug. 2002.
Search in Google Scholar Back to article
[18] A. Paszke et al., “PyTorch: An imperative style, high-performance deep learning library,” arXiv, no. 1912.01703, Dec. 2019.
Search in Google Scholar Back to article
[19] J. Y. Hong, S. H. Park, and J. G. Baek, “Segmented dynamic time warping based signal pattern classification,” in 22nd IEEE International Conference on Computational Science and Engineering and 17th IEEE International Conference on Embedded and Ubiquitous Computing, CSE/EUC 2019, New York, NY, USA, Aug. 2019, pp. 263–265. https://doi.org/10.1109/CSE/EUC.2019.0005810.1109/CSE/EUC.2019.00058
Search in Google Scholar Back to article

Time Series Forecasting of Mobile Robot Motion Sensors Using LSTM Networks

Abstract

Paradigm

My account