Fusing Visuo-Tactile Perception into Kernelized Synergies for Robust Grasping and Fine Manipulation of Non-rigid Objects
This work addresses the challenge of handling non-rigid objects in robotics, which is incremental as it builds on an existing framework by adding perception modules.
The researchers tackled the problem of robust grasping and fine manipulation of non-rigid objects by augmenting a kernelized synergies framework with visuo-tactile perception, resulting in validated stable grasping and dexterous manipulation capabilities in experiments with a robot arm-hand system.
Handling non-rigid objects using robot hands necessities a framework that does not only incorporate human-level dexterity and cognition but also the multi-sensory information and system dynamics for robust and fine interactions. In this research, our previously developed kernelized synergies framework, inspired from human behaviour on reusing same subspace for grasping and manipulation, is augmented with visuo-tactile perception for autonomous and flexible adaptation to unknown objects. To detect objects and estimate their poses, a simplified visual pipeline using RANSAC algorithm with Euclidean clustering and SVM classifier is exploited. To modulate interaction efforts while grasping and manipulating non-rigid objects, the tactile feedback using T40S shokac chip sensor, generating 3D force information, is incorporated. Moreover, different kernel functions are examined in the kernelized synergies framework, to evaluate its performance and potential against task reproducibility, execution, generalization and synergistic re-usability. Experiments performed with robot arm-hand system validates the capability and usability of upgraded framework on stably grasping and dexterously manipulating the non-rigid objects.