At UCL RoMA Lab, we scale foundation models to Visual–Language–Action (VLA) systems for robotics, transforming multimodal perception into intelligent, goal-directed behavior. Our work explores VLA systems built on vision–language and world models, enabling perception, reasoning, and control in embodied settings. We advance embodied AI by tackling generalization across different sensors and tasks, computational efficiency on resource-constrained hardware, and trustworthy human–robot interaction, with the goal of enabling autonomous systems that operate reliably in complex, dynamic environments. {% include section.html %}
{% capture text %}
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.
{% include button.html link="research" text="Learn more about our research" icon="fa-solid fa-arrow-right" flip=true style="bare" %}
{% endcapture %}
{% include feature.html image="images/research_cover.png" link="research" title="Our Research" text=text flip=true %}
{% capture text %}
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.
{% include button.html link="team" text="Meet our team" icon="fa-solid fa-arrow-right" flip=true style="bare" %}
{% endcapture %}
{% include feature.html image="images/team_cover.png" link="team" title="Our Team" text=text %}