Benchmarking the Sim-to-Real Gap in Cloth Manipulation

David Blanco-Mulero, Oriol Barbany, Gokhan Alcan, Adria Colome, Carme Torras, Ville Kyrki

Research output: Contribution to journalArticleScientificpeer-review

27 Downloads (Pure)


Realistic physics engines play a crucial role for learning to manipulate deformable objects such as garments in simulation. By doing so, researchers can circumvent challenges such as sensing the deformation of the object in the realworld. In spite of the extensive use of simulations for this task, few works have evaluated the reality gap between deformable object simulators and real-world data. We present a benchmark dataset to evaluate the sim-to-real gap in cloth manipulation. The dataset is collected by performing a dynamic as well as a quasi-static cloth manipulation task involving contact with a rigid table. We use the dataset to evaluate the reality gap, computational time, and simulation stability of four popular deformable object simulators: MuJoCo, Bullet, Flex, and SOFA. Additionally, we discuss the benefits and drawbacks of each simulator. The benchmark dataset is open-source. Supplementary material, videos, and code, can be found at <uri></uri>.

Original languageEnglish
Pages (from-to)2981-2988
Number of pages8
JournalIEEE Robotics and Automation Letters
Issue number3
Publication statusPublished - 2024
MoE publication typeA1 Journal article-refereed


  • Benchmark testing
  • bimanual manipulation
  • Data sets for robot learning
  • deformable object manipulation
  • Dynamics
  • Engines
  • Fabrics
  • Manipulator dynamics
  • Task analysis
  • Trajectory


Dive into the research topics of 'Benchmarking the Sim-to-Real Gap in Cloth Manipulation'. Together they form a unique fingerprint.

Cite this