Towards Latent Space Based Manipulation of Elastic Rods using Autoencoder Models and Robust Centerline Extractions
This work addresses the challenge of deformable object manipulation for robotics, but it is incremental as it builds on existing methods for specific tasks.
The study tackled the problem of automatically manipulating elastic rods into desired 2D shapes by developing a vision-based controller using a deep autoencoder for shape representation and an online algorithm to handle unknown mechanical properties, achieving real-time centerline extraction and validation through simulations and experiments.
The automatic shape control of deformable objects is a challenging (and currently hot) manipulation problem due to their high-dimensional geometric features and complex physical properties. In this study, a new methodology to manipulate elastic rods automatically into 2D desired shapes is presented. An efficient vision-based controller that uses a deep autoencoder network is designed to compute a compact representation of the object's infinite-dimensional shape. An online algorithm that approximates the sensorimotor mapping between the robot's configuration and the object's shape features is used to deal with the latter's (typically unknown) mechanical properties. The proposed approach computes the rod's centerline from raw visual data in real-time by introducing an adaptive algorithm on the basis of a self-organizing network. Its effectiveness is thoroughly validated with simulations and experiments.