Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
This lecture explores how humans adapt hand poses in bimanual fine manipulation tasks based on task conditions, such as goals and objects. The instructor presents an experimental task involving force sensors and different conditions with varying degrees of freedom. Hand pose analysis is discussed, focusing on the assignment of virtual fingers and the ability to generate force and torque. The lecture also covers the decoupling of force and torque control, observed in different hand pose categories. Conclusions highlight how humans decentralize the assignment of virtual fingers between hands to reduce reliance on single-hand dexterity and lower finger control complexity.