Heading Judgment for the Waist-Mounted MIMU Using LSTM

Shanzhi Gu, Chao Guo

Abstract: In many athlete or firefighter training practices, such as firefighter rescue training or football player dribbling, many movement trajectories will be generated. Recording the exercise data of these trainees can replay the training process and help to improve their learning. In the generation of motion trajectory, the judgment of the motion heading matters and attracts lots of attentions. A large amount of researches have focused on the foot-mounted Miniature Inertial Measurement Unit (MIMU), mainly relying on zero-velocity update (ZUPT) to maintain accuracy. However, ZUPT fails to estimate the gyroscope drift errors, causing the heading angle drifts over time. In this paper, we introduce the waist-mounted MIMU for heading judgment based on deep learning algorithms to alleviate the heading angle drift problem. Although the market is more demanding for the waist-mounted module, there are fewer applications due to its insufficient accuracy. In order to improve the heading judgment of waist-mounted model, we propose to use the stacked LSTM model which we prove is powerful to assist the traditional Pedestrian Dead Reckoning (PDR) in the trajectory drawing, and thus is helpful for the heading judgment. Experimental results show that the proposed model has satisfactory performance in heading judgment.