Abstract PDF BibTeX Website

Fabric manipulation has applications in folding	blankets, handling patient clothing, and protecting items with covers. It is challenging for robots to perform fabric manipulation since fabrics have infinite-dimensional configuration spaces, complex dynamics, and may be in folded or crumpled configurations with severe self-occlusions. Prior work on robotic fabric manipulation relies either on heavily engineered setups or learning-based approaches that create and train on robot-fabric interaction data. In this paper, we propose GPT-Fabric for the canonical tasks of fabric folding and smoothing, where GPT directly outputs an action informing a robot where to grasp and pull a fabric. We perform extensive experiments in simulation to test GPT-Fabric against prior state of the art methods for folding and smoothing. We obtain comparable or better performance to most methods even without explicitly training on a fabric-specific dataset (i.e., zero-shot manipulation). Furthermore, we apply GPT-Fabric in physical experiments over 12 folding and 10 smoothing rollouts. Our results suggest that GPT-Fabric is a promising approach for high-precision fabric manipulation tasks.

@article{GPTFabric2024,
  title={GPT-Fabric: Folding and Smoothing Fabric by Leveraging Pre-Trained Foundation Models},
  author={Vedant Raval and Enyu Zhao and Hejia Zhang and Stefanos Nikolaidis and Daniel Seita},
  journal={arXiv preprint arXiv:2406.09640},
  Year={2024}
}

Abstract PDF BibTeX

We consider the problem of efficiently inferring interventional distributions in a causal Bayesian network from a finite number of observations. Let P be a causal model on a set V of observable variables on a given causal graph G. For sets X, Y⊆V and setting x to X, Px(Y) denotes the interventional distribution on Y with respect to an intervention x to variables X. Shpitser and Pearl (AAAI 2006), building on the work of Tian and Pearl (AAAI 2001), proved that the ID algorithm is sound and complete for recovering Px(Y) from observations. We give the first provably efficient version of the ID algorithm. In particular, under natural assumptions, we give a polynomial-time algorithm that on input a causal graph G on observable variables V, a setting x of a set X⊆V of bounded size, outputs succinct descriptions of both an evaluator and a generator for a distribution P^ that is epsilon-close (in total variation distance) to Px(Y) where Y=V\X, if Px(Y) is identifiable. We also show that when Y is an arbitrary subset of V\X, there is no efficient algorithm that outputs an evaluator of a distribution that is epsilon-close to Px(Y) unless all problems that have statistical zero-knowledge proofs, including the Graph Isomorphism problem, have efficient randomized algorithms.

@inproceedings{bhattacharyya2022efficient,
  title={Efficient interventional distribution learning in the PAC framework},
  author={Bhattacharyya, Arnab and Gayen, Sutanu and Kandasamy, Saravanan and Raval, Vedant and Variyam, Vinodchandran N},
  booktitle={International Conference on Artificial Intelligence and Statistics},
  pages={7531--7549},
  year={2022},
  organization={PMLR}
}