Mehrshad Zandigohar
Papers
3
Total Citations
56
H-Index
3
About
Mehrshad Zandigohar is a researcher specializing in human-robot interaction, prosthetic hand control, and intelligent signal processing, with a particular focus on restoring functional capability to upper-limb amputees. His work sits at the intersection of biomedical engineering, machine learning, and computer vision, addressing one of the most persistent challenges in assistive robotics: accurately decoding human movement intent from physiological signals. Zandigohar's most impactful contribution is his development of multimodal fusion frameworks that combine electromyography (EMG) with computer vision to infer grasp intent for robotic prosthetic hands. Recognizing that EMG signals alone are vulnerable to motion artifacts and muscle fatigue, he pioneered approaches that integrate visual context to dramatically improve inference reliability — work that has garnered 44 citations and represents a meaningful advance in prosthetic control methodology. His complementary research on detecting upcoming grasp type during reach-to-grasp movements further demonstrates his commitment to real-time, anticipatory control systems that feel natural to users. Collectively accumulating over 56 citations, Zandigohar's research offers promising pathways toward prosthetic devices that are more intuitive, robust, and responsive — work with direct implications for improving the quality of life of amputees worldwide.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3