mlsanityData to 7 Oct 2026

Benchmarking the Sim-to-Real Gap in Cloth Manipulation

arXiv 2310.09543 ↗First posted 14 Oct 2023cs.RO cs.CV cs.LGcited by 14

Not on the map. Why?

Abstract (arXiv)

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 https://sites.google.com/view/cloth-sim2real-benchmark.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 27 of its 41 references that are in the map. First posted on arXiv 14 Oct 2023.

Builds on

27 of 41 references.

References · 27

  1. 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,455
  2. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  3. 2018Open3D: A Modern Library for 3D Data Processingcited by 717
  4. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 699
  5. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  6. 2020robosuite: A Modular Simulation Framework and Benchmark for Robot Learningcited by 484
  7. 2021Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusioncited by 129
  8. 2018Sim-to-Real Reinforcement Learning for Deformable Object Manipulationcited by 124
  9. 2020SoftGym: Benchmarking Deep Reinforcement Learning for Deformable Object Manipulationcited by 118
  10. 2021FlingBot: The Unreasonable Effectiveness of Dynamic Manipulation for Cloth Unfoldingcited by 80
  11. 2020Learning to Rearrange Deformable Cables, Fabrics, and Bags with Goal-Conditioned Transporter Networkscited by 77
  12. 2019Learning to Manipulate Deformable Objects without Demonstrationscited by 76
15 more
  1. 2020Learning Predictive Representations for Deformable Objects Using Contrastive Estimationcited by 72
  2. 2021Planar Robot Casting with Real2Sim2Real Self-Supervised Learningcited by 38
  3. 2022Iterative Residual Policy: for Goal-Conditioned Dynamic Manipulation of Deformable Objectscited by 36
  4. 2022DiffCloud: Real-to-Sim from Point Clouds with Differentiable Simulation and Rendering of Deformable Objectscited by 29
  5. 2019Dynamic Cloth Manipulation with Deep Reinforcement Learningcited by 26
  6. 2022DaXBench: Benchmarking Deformable Object Manipulation with Differentiable Physicscited by 22
  7. 2022Learning Deformable Object Manipulation from Expert Demonstrationscited by 18
  8. 2019Learning to Collaborate from Simulation for Robot-Assisted Dressingcited by 16
  9. 2019A Grasping-centered Analysis for Cloth Manipulationcited by 14
  10. 2021Validating Robotics Simulators on Real-World Impactscited by 11
  11. 2021Learning Visual Feedback Control for Dynamic Cloth Foldingcited by 10
  12. 2023Self-supervised Cloth Reconstruction via Action-conditioned Cloth Trackingcited by 8
  13. 2021Household Cloth Object Set: Fostering Benchmarking in Deformable Object Manipulationcited by 7
  14. 2019Benchmarking Simulated Robotic Manipulation through a Real World Datasetcited by 5
  15. 2023QDP: Learning to Sequentially Optimise Quasi-Static and Dynamic Manipulation Primitives for Robotic Cloth Manipulationcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 4; 2026: 6.

14 papers.

Sort:

By area:

  1. 2026LLM-as-a-Verifier: A General-Purpose Verification Frameworkcited by 21
  2. 2025A Survey of Robotic Navigation and Manipulation with Physics Simulators in the Era of Embodied AIcited by 16
  3. 2024Learning Keypoints for Robotic Cloth Manipulation using Synthetic Datacited by 11
  4. 2025BiFold: Bimanual Cloth Folding with Language Guidancecited by 4
  5. 2024D-Cubed: Latent Diffusion Trajectory Optimisation for Dexterous Deformable Manipulationcited by 3
  6. 2026Robustness without Wrinkles: Parallel Simulation and Robust MPC for Certified Deformable Manipulationcited by 3
  7. 2026GAUGE: A Measurement-Grounded Benchmark for Physical Fidelity in Simulation Engines and Video World Modelscited by 3
  8. 2025Implicit Neural-Representation Learning for Elastic Deformable-Object Manipulationscited by 2
  9. 2025Position: Intelligent Science Laboratory Requires the Integration of Cognitive and Embodied AIcited by 2
  10. 2026Tether: Autonomous Functional Play with Correspondence-Driven Trajectory Warpingcited by 2
  11. 2024Dynamic Manipulation of Deformable Objects using Imitation Learning with Adaptation to Hardware Constraintscited by 0
  12. 2024An Open-source Sim2Real Approach for Sensor-independent Robot Navigation in a Gridcited by 0
2 more
  1. 2026Dynamic robotic cloth folding with efficient Koopman operator-based model predictive controlcited by 0
  2. 2026VFILC: Accurate Frequency Extrapolations in Imitation Learning via Sampling Frequency ILCcited by 0