A System for General In-Hand Object Re-Orientation
This addresses a challenging robotics problem for manipulation tasks, with incremental improvements in scalability and transferability.
The paper tackles the problem of in-hand object reorientation in robotics by presenting a model-free framework that learns to reorient over 2000 geometrically different objects with both hand orientations, showing strong zero-shot transfer to new objects and real-world applicability.
In-hand object reorientation has been a challenging problem in robotics due to high dimensional actuation space and the frequent change in contact state between the fingers and the objects. We present a simple model-free framework that can learn to reorient objects with both the hand facing upwards and downwards. We demonstrate the capability of reorienting over 2000 geometrically different objects in both cases. The learned policies show strong zero-shot transfer performance on new objects. We provide evidence that these policies are amenable to real-world operation by distilling them to use observations easily available in the real world. The videos of the learned policies are available at: https://taochenshh.github.io/projects/in-hand-reorientation.