Household Cloth Object Set: Fostering Benchmarking in Deformable Object Manipulation
arXiv:2111.01527 · doi:10.1109/LRA.2022.3158428
Abstract
Benchmarking of robotic manipulations is one of the open issues in robotic research. An important factor that has enabled progress in this area in the last decade is the existence of common object sets that have been shared among different research groups. However, the existing object sets are very limited when it comes to cloth-like objects that have unique particularities and challenges. This paper is a first step towards the design of a cloth object set to be distributed among research groups from the robotics cloth manipulation community. We present a set of household cloth objects and related tasks that serve to expose the challenges related to gathering such an object set and propose a roadmap to the design of common benchmarks in cloth manipulation tasks, with the intention to set the grounds for a future debate in the community that will be necessary to foster benchmarking for the manipulation of cloth-like objects. Some RGB-D and object scans are also collected as examples for the objects in relevant configurations. More details about the cloth set are shared in http://www.iri.upc.edu/groups/perception/ClothObjectSet/HouseholdClothSet.html.
Submitted
References in corpus (1)
Cited by in corpus (5)
- Benchmarking the Sim-to-Real Gap in Cloth Manipulation
- QDP: Learning to Sequentially Optimise Quasi-Static and Dynamic Manipulation Primitives for Robotic Cloth Manipulation
- Center Direction Network for Grasping Point Localization on Cloths
- Standardization of Cloth Objects and its Relevance in Robotic Manipulation
- A Dataset and Benchmark for Robotic Cloth Unfolding Grasp Selection: The ICRA 2024 Cloth Competition