Max Robotics — Global Service Robot Directory + US Certification

About

Amir Hasan Monadjemi is a pioneering researcher in biologically inspired robotics, with a primary focus on humanoid locomotion and neural control systems. His work bridges the gap between computational neuroscience and practical robotics, particularly through the development of central pattern generators (CPGs) for bipedal walking. Monadjemi’s most significant contribution is the introduction of a biologically inspired layered learning framework for humanoid robots, which has garnered 19 citations and laid the groundwork for adaptive robotic gait generation. He has also advanced curvilinear bipedal walking by integrating policy gradient methods with programmable CPGs, enabling Nao humanoid robots to learn complex, non-linear walking patterns. His modeling of the mesencephalic locomotor region (MLR) for robotic control—cited 8 times—demonstrates a unique approach to replicating vertebrate locomotion structures in artificial systems. Additionally, Monadjemi has innovated in neural network design, training oscillatory neural networks with natural gradient particle swarm optimization to generate rhythmic outputs for walking. His recent work on robotic puppetry using natural learner unit pattern generators (2024) shows his continued exploration of neural-inspired control. With a total citation count exceeding 50 across his key papers, Monadjemi’s research has significantly influenced the field of humanoid robotics, offering elegant solutions for stable, adaptive locomotion that draw directly from nature’s blueprints.