Max Robotics — Global Service Robot Directory + US Certification

About

Paniz Sedighi is at the forefront of advancing human-robot interaction, with a primary focus on developing intelligent, adaptive control systems for upper-limb assistive exoskeletons. Her research masterfully integrates surface electromyography (sEMG), deep learning, and shared control paradigms to decode user intention in real-time. Her most cited work, “EMG-Based Intention Detection Using Deep Learning for Shared Control in Upper-Limb Assistive Exoskeletons” (2023, 53 citations), established a foundational framework for predicting user movement intent, a critical step toward seamless human-robot collaboration. Building on this, Sedighi has pioneered the use of hybrid CNN-LSTM networks with attention mechanisms to fuse EMG and IMU signals, enabling more accurate and responsive myoelectric control. Her recent contributions include a few-shot learning approach via meta-learning, which allows exoskeletons to rapidly personalize their control to individual users’ unique muscle patterns—a significant leap toward practical, user-friendly assistive technologies. Beyond exoskeletons, she has also contributed to surgical robotics, developing a realistic simulator for non-rigid, contact-rich manipulation on the da Vinci Research Kit. With a growing citation record and a clear trajectory toward personalized, real-time robotic assistance, Sedighi is shaping the future of intuitive, adaptive robotic systems for both rehabilitation and surgery.