# Learning Closed-loop Dough Manipulation Using a Differentiable Reset Module

arXiv: https://arxiv.org/abs/2207.04638 · HTML: https://mlsanity.com/paper/2207.04638/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jul 2022.

## Built on by (most cited first, 11 of 11)

- [DoughNet: A Visual Predictive Model for Topological Manipulation of Deformable Objects](https://mlsanity.com/paper/2404.12524/) (2024)
- [SculptDiff: Learning Robotic Clay Sculpting from Humans with Goal Conditioned Diffusion Policy](https://mlsanity.com/paper/2403.10401/) (2024)
- [Self-Refining Vision Language Model for Robotic Failure Detection and Reasoning](https://mlsanity.com/paper/2602.12405/) (2026)
- [Learning Generalizable Tool-use Skills through Trajectory Generation](https://mlsanity.com/paper/2310.00156/) (2023)
- [GenDOM: Generalizable One-shot Deformable Object Manipulation with Parameter-Aware Policy](https://mlsanity.com/paper/2309.09051/) (2023)
- [Collective Intelligence for 2D Push Manipulations with Mobile Robots](https://mlsanity.com/paper/2211.15136/) (2022)
- [Non-rigid Relative Placement through 3D Dense Diffusion](https://mlsanity.com/paper/2410.19247/) (2024)
- [Manipulating Elasto-Plastic Objects With 3D Occupancy and Learning-Based Predictive Control](https://mlsanity.com/paper/2505.16249/) (2025)
- [GenORM: Generalizable One-shot Rope Manipulation with Parameter-Aware Policy](https://mlsanity.com/paper/2306.09872/) (2023)
- [PinchBot: Long-Horizon Deformable Manipulation with Guided Diffusion Policy](https://mlsanity.com/paper/2507.17846/) (2025)
- [Estimating Material Properties of Interacting Objects Using Sum-GP-UCB](https://mlsanity.com/paper/2310.11749/) (2023)

## Abstract (arXiv)

Deformable object manipulation has many applications such as cooking and laundry folding in our daily lives. Manipulating elastoplastic objects such as dough is particularly challenging because dough lacks a compact state representation and requires contact-rich interactions. We consider the task of flattening a piece of dough into a specific shape from RGB-D images. While the task is seemingly intuitive for humans, there exist local optima for common approaches such as naive trajectory optimization. We propose a novel trajectory optimizer that optimizes through a differentiable "reset" module, transforming a single-stage, fixed-initialization trajectory into a multistage, multi-initialization trajectory where all stages are optimized jointly. We then train a closed-loop policy on the demonstrations generated by our trajectory optimizer. Our policy receives partial point clouds as input, allowing ease of transfer from simulation to the real world. We show that our policy can perform real-world dough manipulation, flattening a ball of dough into a target shape.