FolDeX: A Physical-World Benchmark for Long-Horizon Robotic Manipulation of Deformable Objects

FolDeX: A Physical-World Benchmark for Long-Horizon Robotic Manipulation of Deformable Objects

|Authors: Chenhuan Liu, Yi Xu, Feng Wu, Hanyang Wang, Wenxiao Kuai, Weihao Ding, Shan Wang, Yang Liu, Shuyong Gao, Wenqiang Zhang

|Venue: arXiv preprint | Year: 2026

|arXiv: 2609.10243v1

Abstract

Embodied AI, including vision-language-action and world-action models, must operate reliably in the physical world. Yet methods that perform well in simulation can degrade substantially on real robots, especially in long-horizon deformable-object manipulation, where policies must track changing states and execute reliable multi-stage bimanual interactions. Existing real-robot benchmarks mainly focus on short-horizon rigid-object tasks and offer limited coverage of long-horizon deformable manipulation. We introduce FolDeX, a physical-world benchmark built entirely from real-robot data, with garment folding as its primary task. Since real-robot data collection is costly, FolDeX studies how heterogeneous physical experience can be reused efficiently. The benchmark is organized around four research axes: leveraging human intervention and recovery data collected during deployment; transferring data across tasks, including across garment categories and from rigid to deformable-object manipulation; reusing data across scenes with changes in lighting, background, and layout; and transferring data across robotic embodiments. FolDeX provides 2,000+ hours of real-robot data spanning 20+ tasks and 10+ embodiments. We also establish a fair real-robot evaluation platform for externally submitted policies, with standardized tasks, held-out physical objects, controlled initializations, and a unified execution protocol. The platform is publicly accessible at https://ai.midea.com/#/fold-challenge. We hope FolDeX will serve as a unified testbed for heterogeneous real-robot data reuse and reliable long-horizon deformable manipulation.

Key Contributions

• Embodied AI, including vision-language-action and world-action models, must operate reliably in t…
• Yet methods that perform well in simulation can degrade substantially on real robots, especially …
• Existing real-robot benchmarks mainly focus on short-horizon rigid-object tasks and offer limited…
• We introduce FolDeX, a physical-world benchmark built entirely from real-robot data, with garment…
• Since real-robot data collection is costly, FolDeX studies how heterogeneous physical experience …

Topics

• manipulation
• vision
• vla
• reinforcement-learning
• control
• benchmark

Code & Data

No code repository linked in paper metadata.

BibTeX

@article{Liu2026_260910243v1,
  title     = {FolDeX: A Physical-World Benchmark for Long-Horizon Robotic Manipulation of Deformable Objects},
  author    = {Chenhuan Liu and Yi Xu and Feng Wu and Hanyang Wang and Wenxiao Kuai and Weihao Ding and Shan Wang and Yang Liu and Shuyong Gao and Wenqiang Zhang},
  year      = {2026},
  eprint    = {2609.10243v1},
  archivePrefix = {arXiv},
  primaryClass  = {cs.RO},
  url       = {https://arxiv.org/abs/2609.10243v1}
}