Max Robotics — Global Service Robot Directory + US Certification

About

A. Sideris is a leading researcher in robotics, control systems, and sensor fusion, whose work has advanced both the theoretical foundations and practical applications of autonomous systems. His most influential contribution is the landmark 1992 paper "Learning convergence in the cerebellar model articulation controller" (157 citations), which provided the first rigorous proof that the CMAC neural network learning algorithm always converges with arbitrary accuracy on any training dataset—a fundamental result that reshaped understanding of adaptive control and machine learning in robotics. Sideris has also made significant strides in low-cost sensing, notably developing state estimation techniques that combine inexpensive accelerometers and rate gyros with low-bandwidth tilt sensors to achieve high-bandwidth inclination measurements (59 citations). This work has enabled more robust and affordable attitude estimation for mobile robots and drones. His research extends to dynamic balance control, including innovative approaches for under-actuated hopping robots that combine pneumatic actuation with Acrobot-like structures. Through his algorithmic optimization of robot motion and structured learning in neural networks for trajectory control, Sideris has consistently bridged theory and practice, earning recognition as a pioneer in making intelligent robotic systems both more reliable and more accessible.