Papers
5
Total Citations
70
H-Index
3
About
Ali Marjaninejad is a robotics and bioengineering researcher whose work sits at the intersection of bio-inspired machine learning, tendon-driven robotic systems, and autonomous motor control. His research draws inspiration from biological musculoskeletal systems to address fundamental challenges in designing and controlling anthropomorphic robots — particularly those driven by compliant tendons, which mimic the mechanical complexity of human limbs. Marjaninejad's most influential contribution, "Autonomous functional movements in a tendon-driven limb via limited experience" (2019, 41 citations), demonstrated that robotic limbs can acquire functional motor behaviors with remarkably little training data, a breakthrough with profound implications for adaptive robotics. His work on redundancy in anthropomorphic systems further interrogates core assumptions in robot design, while his "insideOut" framework and related studies on non-collocated sensing offer elegant, biologically motivated solutions for estimating limb posture without traditional joint encoders — reducing mechanical complexity and improving robustness. His investigations into kinematic feedback additionally show how simple error signals can dramatically accelerate autonomous learning. Collectively, Marjaninejad's research advances a vision of robots that learn and adapt more like living organisms, making him a notable voice in the emerging field of biologically inspired autonomous robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2Should Anthropomorphic Systems be “Redundant”?16 citations · 2018
- 3
- 4
- 5