NIST Task Board #3

Automatic manipulation of linear flexible objects is computationally expensive due to their infinite degrees of freedom in the free spaces. Manipulating such objects in a constrained space raises more challenges due to restricted robot motions.

In this work, we designed a pipeline for automating the manipulation of DLOs in the constrained spaces. The pipeline contains a geometric model of cable-like objects based on multimodal features including point cloud, color, and shape. With the estimated 3-D cable model and environment information, we implemented a visual servoing (VS) based planning methodology for manipulating the cable in the constrained spaces. We demonstrate the efficiency and robustness of our method by automating a cable threading task from the Task Board #3 designed by the National Institute of Standards and Technology with real robot (Kinova Gen3) experiments.