Max Robotics — Global Service Robot Directory + US Certification

About

Jin Han Lee is a robotics and computer vision researcher whose work spans autonomous navigation, deep reinforcement learning, and privacy-preserving imaging. His most influential contribution, "Goal-Driven Autonomous Exploration Through Deep Reinforcement Learning" (2021), has garnered 167 citations and demonstrates his ability to architect intelligent systems that enable robots to navigate unknown environments by identifying points of interest and selecting optimal waypoints autonomously. This work, complemented by his 2021 research on goal-driven autonomous mapping that integrates reactive and planned navigation, positions him as a significant voice in the field of embodied AI and robotic exploration. Lee's 2020 paper on goal-oriented obstacle avoidance in continuous action spaces (44 citations) further showcases his expertise in translating deep reinforcement learning theory into practical robotic motion control. Beyond robotics, his work on CLEANIR (27 citations) reveals a broader intellectual curiosity, addressing pressing privacy concerns by developing a controllable identity-removal system that preserves image naturalness without blurring or masking. His earlier work on scene-based indoor navigation using topological Bayesian frameworks rounds out a research portfolio that consistently bridges perception, learning, and real-world deployment — making his publications essential reading for students exploring autonomous systems and intelligent robotics.