SoftMimicGen: A Data Generation System for Scalable Robot Learning in Deformable Object Manipulation

2026-03-26

AI Summary

This work addresses the scarcity of real-world data and the lack of high-fidelity synthetic data generation methods that currently limit robotic learning for deformable object manipulation. We present the first large-scale synthetic data generation framework tailored to this domain, integrating high-fidelity physics simulation, an automated data pipeline, and modeling of multiple robotic platforms. The framework encompasses a diverse set of deformable objects, complex manipulation actions, and four distinct robot systems. The resulting high-quality dataset effectively supports imitation learning and policy training, significantly reducing reliance on real-world data while enhancing policy generalization. This approach fills a critical gap in simulation capabilities and data availability for deformable object manipulation tasks.

Technology Category

• Intelligent Robots: Manipulation
• Machine Learning: Imitation Learning & Inverse Reinforcement Learning
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Web Mining and Content Analysis: Web data generation and simulation
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

Abstract

Large-scale robot datasets have facilitated the learning of a wide range of robot manipulation skills, but these datasets remain difficult to collect and scale further, owing to the intractable amount of human time, effort, and cost required. Simulation and synthetic data generation have proven to be an effective alternative to fuel this need for data, especially with the advent of recent work showing that such synthetic datasets can dramatically reduce real-world data requirements and facilitate generalization to novel scenarios unseen in real-world demonstrations. However, this paradigm has been limited to rigid-body tasks, which are easy to simulate. Deformable object manipulation encompasses a large portion of real-world manipulation and remains a crucial gap to address towards increasing adoption of the synthetic simulation data paradigm. In this paper, we introduce SoftMimicGen, an automated data generation pipeline for deformable object manipulation tasks. We introduce a suite of high-fidelity simulation environments that encompasses a wide range of deformable objects (stuffed animal, rope, tissue, towel) and manipulation behaviors (high-precision threading, dynamic whipping, folding, pick-and-place), across four robot embodiments: a single-arm manipulator, bimanual arms, a humanoid, and a surgical robot. We apply SoftMimicGen to generate datasets across the task suite, train high-performing policies from the data, and systematically analyze the data generation system. Project website: \href{https://softmimicgen.github.io}{softmimicgen.github.io}.

Problem

• deformable object manipulation
• synthetic data generation
• robot learning
• simulation
• scalable datasets

Innovation

• deformable object manipulation
• synthetic data generation
• high-fidelity simulation
• scalable robot learning
• SoftMimicGen