- © RBO
Unlike most robot grippers, human hands are versatile manipulators: they are soft, compliant, dexterous, and can be used for multiple tasks at once (e.g. lifting a teacup while holding a pencil in the same hand, which requires repositioning of the pencil to free the other fingers for gripping the cup handle).
We want robotic hands to be similarly versatile. The RBO Hand 3 already solves a large part of this problem by mimicking the morphology of a human hand, but planning movements is still a hard problem. Conventional manipulation planners are designed for rigid hands with links, and they employ analytic models of the hand and a previously known object. Such models cease to be useful in our case, because it is hard to precisely model a system with a soft hand and a complex unknown object.
With these constraints in place, how can our soft robotic hands be made to grasp a pencil and move it between different fingers, or spin a cube to an arbitrary face?
To tackle this problem, we aim to use model-free methods enriched with prior knowledge of the task at hand - both from classical control and Reinforcement Learning (RL) - to find robust closed-loop control policies. Additionally, we are going to rethink In-Hand-Manipulation as a form of impedance control leveraging contact information instead of a position-control problem.
This effort will include investigations of different feature encodings, sample-efficient learning algorithms, appropriate simulation environments and various kinds of hand sensorization .
Contact: Adrian Sieler , Aditya Bhatt 
- © AvH
Deutsche Forschungsgemeinschaft (DFG, German Research
Foundation) under Germany's Excellence Strategy - EXC 2002/1
"Science of Intelligence" - project number 390523135.
SoMa - Soft Manipulation , Horizon 2020 project funded by the
European Commission. May 2015 - April 2019.
Alexander von Humboldt professorship  - awarded by the Alexander
von Humboldt foundation  and funded through the Ministry of
Education and Research, BMBF ,
July 2009 - June 2015