The Scalable Whole-body Intelligent Robot Learning (SWIRL) Lab pushes the boundaries of robot learning by developing systems that leverage their entire physical embodiment. We combine reinforcement learning, imitation learning, and large-scale foundation models to build robots whose skills scale with data, compute, and experience, with a relentless focus on sample efficiency and generalisation.

Our vision is simple yet ambitious: create robots that learn efficiently, adapt quickly, and act capably in complex, dynamic environments alongside humans.