# Sim-to-Real Gentle Manipulation of Deformable and Fragile Objects with Stress-Guided Reinforcement Learning

arXiv: https://arxiv.org/abs/2510.25405 · HTML: https://mlsanity.com/paper/2510.25405/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods.
- Builds on 22 of its 39 references that are in the map.
- First posted on arXiv 29 Oct 2025.

## Placed in

- Deep reinforcement learning methods / [RL for robot locomotion and manipulation](https://mlsanity.com/deeprl/rl-for-robot-locomotion-and-manipulation/)

## Builds on (most cited first, 22 of 22)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Learning Dexterous In-Hand Manipulation](https://mlsanity.com/paper/1808.00177/) (2018)
- [Behavioral Cloning from Observation](https://mlsanity.com/paper/1805.01954/) (2018)
- [Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey](https://mlsanity.com/paper/2003.04960/) (2020)
- [Efficient Online Reinforcement Learning with Offline Data](https://mlsanity.com/paper/2302.02948/) (2023)
- [DiffTaichi: Differentiable Programming for Physical Simulation](https://mlsanity.com/paper/1910.00935/) (2019)
- [Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning](https://mlsanity.com/paper/2410.21845/) (2024)
- [Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes](https://mlsanity.com/paper/2408.03539/) (2024)
- [SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning](https://mlsanity.com/paper/2401.16013/) (2024)
- [Sim-to-Real Reinforcement Learning for Deformable Object Manipulation](https://mlsanity.com/paper/1806.07851/) (2018)
- [Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoids](https://mlsanity.com/paper/2502.20396/) (2025)
- [Learning Gentle Object Manipulation with Curiosity-Driven Deep Reinforcement Learning](https://mlsanity.com/paper/1903.08542/) (2019)
- [Sim-To-Real Transfer for Visual Reinforcement Learning of Deformable Object Manipulation for Robot-Assisted Surgery](https://mlsanity.com/paper/2406.06092/) (2024)
- [Bi-Touch: Bimanual Tactile Manipulation with Sim-to-Real Deep Reinforcement Learning](https://mlsanity.com/paper/2307.06423/) (2023)
- [DefGraspNets: Grasp Planning on 3D Fields with Graph Neural Nets](https://mlsanity.com/paper/2303.16138/) (2023)
- [CageCoOpt: Enhancing Manipulation Robustness through Caging-Guided Morphology and Policy Co-Optimization](https://mlsanity.com/paper/2409.11113/) (2024)
- [Toward Force Estimation in Robot-Assisted Surgery using Deep Learning with Vision and Robot State](https://mlsanity.com/paper/2011.02112/) (2020)
- [Grasping Deformable Objects via Reinforcement Learning with Cross-Modal Attention to Visuo-Tactile Inputs](https://mlsanity.com/paper/2504.15595/) (2025)
- [T-DOM: A Taxonomy for Robotic Manipulation of Deformable Objects](https://mlsanity.com/paper/2412.20998/) (2024)
- [Image-to-Force Estimation for Soft Tissue Interaction in Robotic-Assisted Surgery Using Structured Light](https://mlsanity.com/paper/2501.08593/) (2025)
- [DexFruit: Dexterous Manipulation and Gaussian Splatting Inspection of Fruit](https://mlsanity.com/paper/2508.07118/) (2025)

## Built on by (most cited first, 1 of 1)

- [TRACER: Texture-Robust Affordance Chain-of-Thought for Deformable-Object Refinement](https://mlsanity.com/paper/2601.20208/) (2026)

## Abstract (arXiv)

Robotic manipulation of deformable and fragile objects presents significant challenges, as excessive stress can lead to irreversible damage to the object. While existing solutions rely on accurate object models or specialized sensors and grippers, this adds complexity and often lacks generalization. To address this problem, we present a vision-based reinforcement learning approach that incorporates a stress-penalized reward to discourage damage to the object explicitly. In addition, to bootstrap learning, we incorporate offline demonstrations as well as a designed curriculum progressing from rigid proxies to deformables. We evaluate the proposed method in both simulated and real-world scenarios, showing that the policy learned in simulation can be transferred to the real world in a zero-shot manner, performing tasks such as picking up and pushing tofu. Our results show that the learned policies exhibit a damage-aware, gentle manipulation behavior, demonstrating their effectiveness by decreasing the stress applied to fragile objects by 36.5% while achieving the task goals, compared to vanilla RL policies.