FolDeX: A Physical-World Benchmark for Long-Horizon Robotic Manipulation of Deformable Objects
Classification
View four quadrants- Major category
- Benchmarks & simulators
- Quadrant
- Not applicable
- Architecture
- Not applicable
- Prediction paradigm
- Not applicable
- Source review status
- Not assigned
Category review. The primary contribution is a physical garment-manipulation benchmark, recovery/transfer tracks and controlled success/quality evaluation; its reference policy does not turn the benchmark into a WAM. The cataloged contribution is a dataset/data-generation method or evaluation/simulation resource, not the architecture of an evaluated or external policy. Reading evidence
Contribution
FolDeX evaluates complete physical garment-folding episodes and asks whether expensive robot experience can be reused across recovery states, tasks, scenes, and embodiments. Its reference policies use π0. Recovery-augmented training raises reported average success from 80.75% to 95.00%, but transfer studies remain preliminary and the missing quality-scoring appendix prevents independent reconstruction of FoldScore from the supplied paper alone.
Abstract
An abstract has not been added yet.
Affiliations
Fudan University; AI Research Center, Midea Group (Shanghai) Co., Ltd.; Carnegie Mellon University