Freek Stulp

Robots can now explore and learn the geometry of unknown surfaces simultaneously, achieving systematic coverage with minimal prior information.

Voice-commanded surface finishing is now a reality, thanks to a new framework that lets non-experts adapt robot skills through touch, language, and a drag-and-drop interface.

Time-varying stiffness and wrench arbitration in shared control systems can be stabilized without constraining design choices, unlocking more flexible and adaptable robot guidance.

Control a robot with natural language, no fine-tuning required: IROSA uses a tool-based architecture to safely adapt robot skills using pre-trained LLMs.