Dynamic model improves torque estimates for exoskeleton assistance
Assistance Torque Estimation via Dynamics-Aware Optimization for Lower-Limb Exoskeleton in Complex Environments
Robotics
Summary
Estimating the exact force an exoskeleton should provide to assist human joints is normally done with expensive and complex motion capture systems that don't work well outdoors. The authors propose a new way to estimate helpful torque by using a dynamic model that mimics how human motion works, reducing the need for costly data. They then train a network to predict these assistance torques in real time, even outside controlled environments. Their approach leads to better support during walking, lowering physical effort and muscle strain.
What this means in practice
- •For exoskeleton engineers: Use dynamic optimization and data-driven predictions to improve real-time torque control for lower-limb assistive devices in outdoor and complex settings.
- •For rehabilitation therapists: Adopt torque estimation methods that adapt assistance to patient walking patterns without relying on expensive lab equipment.
Authors
Xiao-Yin Liu, Guotao Li, Weiqun Wang, Zeng-Guang Hou
Abstract
Ground-truth human joint torque estimation relies on motion capture systems, which suffer from limited outdoor usability and significant deployment expenses. Furthermore, direct scaling of ground-truth joint torques to obtain motor torque commands is not necessarily the optimal strategy. To address the aforementioned limitations, inspired by the human motion generation process, this paper proposes a novel assistance torque estimation method based on the dynamic model. From an optimization perspective, the proposed method directly generates motor-assist torque and lowers the cost of data acquisition. Then, a data-driven assistance torque prediction network is trained to enable accurate real-time prediction under complex outdoor environments. Experimental results demonstrate that optimized (estimated) assistance torque exhibits better phase consistency with gait trajectories and better alignment with task characteristics. Relative to the Zero torque condition, the predicted torque can decrease metabolic rate by 11.8%-17.7%, heart rate by 8.9%-14.3%, and peak muscle activation levels by 28.2%-54.0%, respectively. This provides a new perspective for low-cost adaptive exoskeleton assistance.