Max Robotics — Global Service Robot Directory + US Certification

About

Hitesh Shah is a researcher whose work sits at the intersection of reinforcement learning, robotics, and intelligent control systems. His primary contributions focus on developing robust, adaptive controllers for robot manipulators operating in uncertain environments—a critical challenge for real-world automation. Shah’s most influential work, "Reinforcement learning control of robot manipulators in uncertain environments" (2009, 12 citations), investigates how reinforcement learning can achieve stable tracking performance despite parameter variations and disturbances. He has pioneered the fusion of reinforcement learning with evolving fuzzy neural networks (2014, 10 citations) and fuzzy decision tree function approximators (2010, 7 citations), demonstrating that these hybrid approaches offer more reliable convergence than traditional neural networks, especially in large-scale problems. Shah has also advanced robust control theory by applying two-player zero-sum Markov game frameworks, as seen in his work on fuzzy decision tree-based robust Markov game controllers (2010, 5 citations). His later research incorporates kernel recursive least-squares support vector machines for continuous state-space reinforcement learning (2012, 5 citations), further extending the toolkit for value function approximation. Through these contributions, Shah has helped bridge the gap between theoretical reinforcement learning algorithms and practical, robust control for robotic systems.