Max Robotics — Global Service Robot Directory + US Certification

About

Kehang Han is a leading researcher at the intersection of robotics, computer vision, and natural language processing, whose work is redefining how machines learn to interact with the physical world. His most impactful contribution is the groundbreaking RT-2 paper (267 citations), which pioneered the concept of vision-language-action models. By demonstrating that a single, end-to-end trained model can directly transfer knowledge from Internet-scale vision-language data into robotic control, Han solved a fundamental challenge in robotics: enabling robots to generalize beyond their training environments and perform emergent semantic reasoning. This work effectively bridges the gap between static web knowledge and dynamic physical action, allowing robots to understand and execute complex commands without task-specific fine-tuning. Han’s research is pivotal in the push toward general-purpose robots, as it shows that large pre-trained models can serve as the cognitive backbone for embodied agents. His contributions are widely recognized for their elegance and practical impact, making him a key figure in the future of autonomous systems and human-robot interaction.