Max Robotics — Global Service Robot Directory + US Certification

About

Shahpour Alirezaee is a robotics researcher whose work spans reinforcement learning, collaborative SLAM, human-robot interaction, and bio-inspired sensing. His most impactful contribution, the 2023 paper "Reinforcement Learning DDPG–PPO Agent-Based Control System for Rotary Inverted Pendulum," has garnered 31 citations, demonstrating his ability to advance control systems through deep reinforcement learning. Alirezaee has also made significant strides in multi-robot systems, with his work on feature-based occupancy map-merging for collaborative SLAM (16 citations) addressing the critical challenge of reducing exploration time through efficient map fusion. His experimental analysis of mirror-like objects in LiDAR-based navigation (16 citations) tackles a persistent problem in modern environments, while his development of a wearable glove for learning-from-demonstration human-robot interaction (9 citations) bridges the gap between human intent and robotic execution. Earlier work includes a low-cost biomimetic central pattern generator based on the AdEx neuron model (8 citations) and a binaural sonar system inspired by bat echolocation (6 citations). His recent 2024 paper on enhancing parameter identification in robot manipulators further solidifies his reputation in industrial robotics. Alirezaee’s research is characterized by its practical focus on real-world deployment, from fatigue balancing to trajectory optimization, making him a notable figure in contemporary robotics.