Learning Dynamical System for Grasping Motion
This work addresses the challenge of coordinated robotic grasping for improved manipulation in dynamic environments, representing an incremental advancement in trajectory encoding methods.
The authors tackled the problem of synchronizing position and orientation in grasping motions by proposing a framework that learns a dynamical system based on a diffeomorphism, achieving effective and adaptable performance in online grasping experiments.
Dynamical System has been widely used for encoding trajectories from human demonstration, which has the inherent adaptability to dynamically changing environments and robustness to perturbations. In this paper we propose a framework to learn a dynamical system that couples position and orientation based on a diffeomorphism. Different from other methods, it can realise the synchronization between positon and orientation during the whole trajectory. Online grasping experiments are carried out to prove its effectiveness and online adaptability.