Transportation robot battery power forecasting based on bidirectional deep-learning method. Issue 3 (22nd February 2020)

• Record Type: Journal Article
• Authors: Thurow, Kerstin; Chen, Chao; Junginger, Steffen; Stoll, Norbert; Liu, Hui
• Is Part Of: Transportation safety and environment. Volume 1:Issue 3(2019)
• Page Start: 205
• Page End: 211
• Publication Date: 2020-02-22
• Subjects: robotic power management -- transportation robot -- time series forecasting -- wavelet packet decomposition -- bidirectional long short-term memory; Transportation engineering -- Periodicals; Transportation -- Safety measures -- Periodicals; 629.04
• DOI: 10.1093/tse/tdz016
• Languages: English
• ISSNs: 2631-4428

Abstract

Abstract: This paper proposes a data-driven hybrid model for forecasting the battery power voltage of transportation robots by combining a wavelet method and a bidirectional deep-learning technique. In the proposed model, the on-board battery power data is measured and transmitted. A WPD (wavelet packet decomposition) algorithm is employed to decompose the original collected non-stationary series into several relatively more stable subseries. For each subseries, a deep learning–based predictor – bidirectional long short-term memory (BiLSTM) – is constructed to forecast the battery power voltage from one step to three steps ahead. Two experiments verify the effectiveness and generalization ability of the proposed hybrid forecasting model, which shows the highest forecasting accuracy. The obtained forecasting results can be used to decide whether the robot can complete the given task or needs to be recharged, providing effective support for the safe use of transportation robots.