Max Robotics — Global Service Robot Directory + US Certification

About

Niluthpol Chowdhury Mithun is a leading researcher at the intersection of computer vision and robotics, specializing in intelligent visual navigation and semantic scene understanding. His work addresses one of the most critical challenges in autonomous systems: enabling robots to navigate efficiently and robustly in visually degraded or GPS-denied environments. Mithun’s major contributions include the development of **MaAST** (Map Attention with Semantic Transformers), a learning-based framework that leverages deep reinforcement learning and attention mechanisms to dramatically improve the computational efficiency of visual navigation. He also pioneered **SIGNAV**, a semantically-informed SLAM system that maintains high performance even in low-visibility conditions, and **Graph2Nav**, a real-time framework that constructs 3D object-relation graphs to guide autonomous navigation. With over 25 citations across his most influential works, Mithun’s research has been recognized for its practical impact on field robotics, particularly in disaster response and underground exploration. His innovative fusion of semantic reasoning with geometric mapping continues to push the boundaries of how machines perceive and move through complex, unstructured environments.