Research

Research

Robots are dependable when the world is arranged for them, and unreliable the moment it is not. The gap opens wherever contact matters. Our work sits between control, which carries guarantees but needs a model, and learning, which brings flexibility but offers no promises. The fields below are where that work runs. Trajectory optimization and the identification of robot dynamic parameters run underneath most of them.

  1. Geometric and Riemannian robot learning

    Learning and control are formulated directly on manifolds and Lie groups, not on flattened approximations of them. This keeps what a robot learns consistent with the structure of the space it moves in.

    4 people · 9 publications since 2024

  2. Safe and certifiable learning-based control

    We establish stability and safety guarantees for robot behaviour. These guarantees still hold when the components producing the behaviour were learned from data rather than designed.

    4 people · 6 publications since 2024

  3. Learning from demonstration and physical interaction

    Robots acquire skills from human demonstration or from their own exploration. These skills then transfer across objects, goals and embodiments.

    2 people · 7 publications since 2024

  4. Compliant and contact-rich manipulation

    We regulate force and impedance in tasks defined by contact. The aim is to keep the robot stable and safe while it touches an object or a person.

    6 publications since 2024

  5. Soft and continuum robotics

    We model, simulate and control bodies whose compliance is structural rather than commanded. Their very many degrees of freedom put them out of reach of classical rigid-body methods.

    2 people · 1 publication since 2024

  6. Decision-making under uncertainty

    We use free-energy and active-inference formulations to treat exploration and robustness as one problem. This lets a robot act well without an exact model of the world.

    1 person · 1 publication since 2024

  7. Neural interfaces and assistive robotics

    We decode human intent from muscle and brain activity. We then close the loop through prosthetic and wearable devices that respond to it.

    1 person · 2 publications since 2024