Zishun Deng

Papers

Total Citations

H-Index

About

Zishun Deng is a rising researcher in the field of biomechatronics and rehabilitation robotics, with a primary focus on intelligent control systems for assistive wearable devices. His work centers on the intersection of deep learning and human motion analysis, particularly for lower-limb exoskeletons designed to restore or enhance mobility. Deng’s most notable contribution is his development of a CNN-LSTM-based framework for motion phase recognition in hip exoskeletons, a critical advancement for real-time, adaptive gait assistance. This approach leverages inertial measurement units (IMUs) to capture angular velocity and acceleration data, enabling precise, sensor-driven phase detection that is essential for safe and effective ankle function during walking. Although early in his career, with his landmark paper already garnering citations, Deng’s work addresses a fundamental bottleneck in exoskeleton technology: the need for robust, non-invasive gait phase estimation. By integrating convolutional and recurrent neural networks, he has demonstrated a scalable method for improving human-robot synchronization. His research holds significant promise for advancing rehabilitation protocols and assistive devices for individuals with gait impairments, marking him as a contributor to watch in the evolving landscape of wearable robotics.