Jaehun Han
Papers
1
Total Citations
21
H-Index
1
About
Jaehun Han is a leading researcher at the intersection of robotics, artificial intelligence, and human-robot interaction, with a primary focus on developing adaptive and socially aware navigation systems. His most impactful work, "Fast Adaptation of Deep Reinforcement Learning-Based Navigation Skills to Human Preference" (2020, 21 citations), addresses a critical limitation in robotic navigation: the inability of deep reinforcement learning (RL) agents to adjust to individual human preferences after training. Han’s key contribution lies in proposing a meta-learning framework that enables robots to rapidly fine-tune their navigation policies—such as preferred speed, proximity, or trajectory style—based on real-time human feedback, without requiring retraining from scratch. This breakthrough bridges the gap between fixed, pre-trained models and the dynamic, personalized expectations of human users in shared spaces. Beyond this, Han’s broader research explores reward shaping, sim-to-real transfer, and multi-agent coordination, consistently pushing toward robots that are not only efficient but also intuitive and trustworthy companions. With his work laying the groundwork for more flexible, user-centric autonomous systems, Han is shaping the future of how robots understand and adapt to the people they serve.
Research Focus
Key Achievements
Top Papers
- 1