At UCL RoMA Lab, we scale Visual-Language-Action (VLA) foundation models for robotics, transforming multimodal perception into intelligent action. Our work advances embodied AI by tackling generalization across diverse sensors, computational efficiency on real-world hardware, and seamless human–robot interaction. The mission is to enable autonomous systems that operate reliably in complex, dynamic environments.
Our Research
We develop advanced foundation models for robotic systems, focusing on multimodal perception, planning, and control. Our research spans computer vision, machine learning, and robotic manipulation.
Our Team
We are building a dynamic team of researchers passionate about robotics and AI, esp. visual-language-action models for robotic applications. We welcome diverse expertise and perspectives.