Sign in Subscribe
Robotics

Robot-Assisted Remote Rehabilitation System for Ankle Fractures Shows Promising Results

Strategic Insights

— 1 min read

A newly developed robot-assisted remote rehabilitation system has shown promising results in enhancing the portability, real-time performance, and safety of postoperative ankle fracture patients' rehabilitation training. The system, proposed by Tianjin University researchers, uses a distributed system architecture and combines a deep learning algorithm with an interpolation fitting method to predict and compensate for time delays in interaction force signals during remote communication.

Key Takeaways:

  • The robotic system is designed to enhance postoperative rehabilitation of ankle fractures, particularly in the home setting, and has a crucial influence on the recovery of lower limb function.
  • The system's hardware enables modular decomposition and facilitates wireless control of the lower controller, with a total weight of 2.634 kg.
  • The system uses a deep learning algorithm and interpolation fitting method to predict and compensate for time delays in interaction force signals, achieving a control frequency of 100 Hz with a maximum normalized root mean square error of 10.89%.
  • The proposed full-cycle rehabilitation training strategy based on adaptive admittance control with system stiffness identification encompasses passive, active-passive, isotonic, and active activities of daily living trainings.
  • Experimental results indicate that the robotic system can execute the training strategies at each phase with high accuracy and safety, and the proposed adaptive control strategy has better compliance than fixed parameter admittance control and fuzzy admittance control methods.
  • The system was financially supported by the China Postdoctoral Science Foundation and the Intelligence Community Postdoctoral Research Fellowship Program.
  • The research was conducted by a team of researchers from Tianjin University, including Tao Sun, Zhiyuan He, Peng Chen, Xinye Wang, and Yuxiang Chen.

Statistics:

  • The robotic system has a total weight of 2.634 kg.
  • The control frequency of the system is elevated to 100 Hz.
  • The maximum normalized root mean square error of the system is 10.89%.
  • 4 different types of rehabilitation trainings are included in the proposed full-cycle training strategy: passive, active-passive, isotonic, and active activities of daily living trainings.
  • The system has better compliance than fixed parameter admittance control and fuzzy admittance control methods.

Sources:

  • A Robot-assisted Remote Rehabilitation System for Ankle Fractures Based On Predictive Force and Full-cycle Training Strategy. Advanced Intelligent Systems, 2025.
  • NewsRx. Reports Summarize Robotics Findings from Tianjin University (A Robot-assisted Remote Rehabilitation System for Ankle Fractures Based On Predictive Force and Full-cycle Training Strategy). Journal of Engineering. October 20, 2025; p 2752.

Read more