Learning dexterous in-hand manipulation

Benchmarking dexterous dual-arm/hand robotic manipulation

DEXMART is a European large-scale integrating project (IP) funded in the Seventh Framework Programme. The acronym stands for DEXterous and autonomous dual-arm/hand robotic manipulation with sMART sensory-motor skills: A bridge from natural to artificial cognition. The project is focused on artificial systems reproducing smart sensory-motor human skills, which operate in unstructured real-world ...

Rotary object dexterous manipulation in hand: a feedback-based method

We focus on manipulating the object of unknown shape, weight and friction properties in hand task. Unlike the traditional method considering the manipulation as multi times grasp planning, we follow the behavior robotics opinion and propose the reactive manipulation strategy. Firstly, we design the compact closed loop control (local controller) to manipulate object in the neighbor area of its c...

In-Hand Dexterous Manipulation of Piecewise-Smooth 3-D Objects

We present an algorithm called nger tracking for in-hand manipulation of three dimensional objects with independent robot ngers. We describe and analyze the diierential control for nger tracking and extend it to on-line continuous control for a set of cooperating robot ngers. We show experimental data from a simulation. Finally, we discuss global control issues for nger tracking and compute low...

Exploring Dexterous Manipulation Workspaces with the iHY Hand

In the past several years, standards in experimental robotics have risen significantly. Robots are increasingly expected to be mobile, self-contained, and robust to the accidental collisions that inevitably accompany work in the real world. These requirements have placed particularly harsh constraints on robot hands. Fingers are also among the smallest and most fragile articulated links in a ro...

Dexterous Object Manipulation via Integrated Hand-Arm Systems