لطفا منتظر بمانید ...
0% Complete
صفحه اصلی
/
سی و چهارمین کنفرانس بین المللی مهندسی برق
A Data-Driven Two-Layer MPC with Safety Filter for Range-of-Motion-Constrained Tracking in a Knee Rehabilitation Exoskeleton
نویسندگان :
Ashkan Jelodar
1
Mohammad Olyai
2
Khalil Alipour
3
Bahram Tarvirdizadeh
4
Majid Sorouri
5
Mohammad Ghamari
6
1- دانشگاه تهران
2- دانشگاه تهران
3- دانشگاه تهران
4- دانشگاه تهران
5- Department of Electronic Engineering, Maynooth University, Maynooth, Co. Kildare, Ireland
6- Electrical Engineering Department, California Polytechnic State University
کلمات کلیدی :
Rehabilitation exoskeleton،knee joint،model predictive control،safety filter،control barrier function،data- driven identification،range of motion
چکیده :
Rehabilitation exoskeletons must track therapeutic joint trajectories while strictly respecting range-of-motion (ROM) limits to protect the user. This paper proposes a practical two-layer control architecture for a 1-DOF knee rehabilitation exoskeleton. First, an offline data-driven identification stage fits a subject-specific linear inverse-dynamics model from measured motion via constrained ridge regression. Second, an online performance-and-safety controller combines linear model predic- tive control (MPC) with a lightweight discrete-time safety filter. The MPC optimizes tracking subject to actuator magnitude and torque-rate limits, while the safety filter solves a scalar quadratic program at each step to enforce a buffered safe set inside the physical ROM under bounded unmodeled accelerations. In simulation with a 20 ms sampling time over a 10 s trial, the controller achieves low tracking error across nominal, high- disturbance, and reduced-torque conditions. In a near-boundary reference case that is intentionally infeasible with respect to the buffered limit, the safety filter intervenes finitely and minimally to maintain safety, whereas a baseline without the safety layer exhibits a small overshoot at the physical ROM bound. The results support the approach as a computationally efficient supervisory safety layer that can be integrated with standard MPC for ROM-constrained rehabilitation control.
لیست مقالات
لیست مقالات بایگانی شده
Techno-Economic Analysis and Experimental Development of a household Anaerobic Biomass Digester for Biogas-Based Electricity Production
Sina Eterafi - Bakhshali Sabery - Mahdi Ebtehaj - Naser Abdollahian
Posture Stabilization of Tractor-Trailer Wheeled Mobile Robot Using Nonlinear MPC
Kevin Babakhanloo - Khalil Alipour - Bahram Tarvirdizadeh - Majid Sorouri - Mohammad Ghamari
تشخیص و تفکیک برخط خطای مدار باز کلید در اینورترهای تک فاز PWM
مهدی اره پناهی - علی اکبر سلیمی
Transfer learning using deep convolutional neural network for predicting dementia severity
Vahid Asayesh - Mehdi Dehghani - Majid Torabi Nikjeh - Sepideh Akhtari khosrowshahi
بهینه سازی تزویج فیبر نوری باریک شده و موجبر نوری بر بستر پلیمر
مهتاب حسینعلی زاده - مونا ثریا - غلام محمد پارسا نسب - شکراله کریمیان
Classifier Fusion Based on Extracted Features Using a Spiking Neural Network from Handwritten Digits
Ali Gholamzade Fard Kazzazi - Malihe Nazari - Fariba Bahrami
A Consensus-Based Approach for Short-Circuit Fault Type Detection in DC Microgrids Using ANFIS
Mohammadreza Mohammadhasani - Javad Sadeh
Electroencephalogram-Based Spinal Cord Injury Signals Decoding Using Temporal-Spatial Dense Deep Convolutional Neural Network
Mohammadreza Abbasi Sardari - Hamed Mirzabagherian - Amir Abolfazl Suratgar - Mohammad Bagher Menhaj
Impacts of Various Wind Turbine Generators on Transient Recovery Voltage in a Medium Voltage Power Network
Mostafa Heydari - Ali Asghar Razi-Kazemi
Using GA and ML to Improve LoRa Network Performance
Yas Hosseini Tehrani - Seyed mojtaba Atarodi
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 44.7.2