Efficient Gait Phase Estimation and Trajectory Prediction in Wearable Devices Using a Dual-Stage Approach

This paper presents a novel dual-stage approach for efficient gait phase recognition and trajectory prediction, tailored for the operation of wearable devices such as exoskeletons. By leveraging dynamic template matching techniques and addressing their computational challenges, we propose an innovative algorithm that significantly enhances both prediction accuracy and computational efficiency. The approach integrates Dynamic Time Warping-KMeans (DTW-KM) template selection in the offline phase and a Soft Constraint Weighted (SCW) template matching technique in the online phase. In the offline stage, the DTW-KM method extracts diverse and generalizable gait patterns from a database, establishing a robust set of templates for future gait recognition. The online stage then adapts to real-time gait dynamics using the SCW method, which incorporates soft constraints and quadratic weighting to improve prediction stability and adaptability to individual gait variations. Preliminary results demonstrate that the algorithm achieves stable gait phase predictions within 0.5–1 s intervals with high efficiency on embedded systems. The dual-stage framework not only ensures scalable and real-time gait prediction performance across varying speeds and conditions but also provides a solid foundation for the deployment of wearable technology in dynamic environments.