Nonprehensile Manipulation Control and Task Planning for Deformable Object Manipulation: Results from the RoDyMan Project

Ruggiero, Fabio; Kim, Jung‐Tae; Gutiérrez–Giles, Alejandro; Satici, Aykut C.; Donaire, Alejandro; Cacace, Jonathan; Buonocore, Luca Rosario; Fontanelli, Giuseppe Andrea; Lippiello, Vincenzo; Siciliano, Bruno

doi:10.1007/978-3-030-31993-9_4

Cited by 2 publications

(1 citation statement)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These works often directly interact with the deformable objects with the robot gripper and use pick-and-place actions as the primitive. However, elastoplastic object manipulation is particularly challenging, as they require rich contact for interacting with the object [28], often with an external tool. Simple action primitives are not sufficient in these cases.…”

Section: Introductionmentioning

confidence: 99%

Learning Closed-Loop Dough Manipulation Using a Differentiable Reset Module

Lin

Held

2022

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

Deformable object manipulation has many applications such as cooking and laundry folding in our daily lives. Manipulating elastoplastic objects such as dough is particularly challenging because dough lacks a compact state representation and requires contact-rich interactions. We consider the task of flattening a piece of dough into a specific shape from RGB-D images. While the task is seemingly intuitive for humans, there exist local optima for common approaches such as naive trajectory optimization. We propose a novel trajectory optimizer that optimizes through a differentiable "reset" module, transforming a single-stage, fixed-initialization trajectory into a multistage, multi-initialization trajectory where all stages are optimized jointly. We then train a closed-loop policy on the demonstrations generated by our trajectory optimizer. Our policy receives partial point clouds as input, allowing ease of transfer from simulation to the real world. We show that our policy can perform real-world dough manipulation, flattening a ball of dough into a target shape. Supplementary videos can be found on our project website: https://sites.google.com/view/dough-manipulation.

show abstract

Section: Introductionmentioning

confidence: 99%