LeHome: A Simulation Environment for Deformable Object Manipulation in Household Scenarios
Zeyi Li, Yushi Yang, Shawn Xie, Jingkai Xu, Tianxing Chen, Yuran Wang, Zhenhao Shen, Yan Shen, Yue Chen, Wenjun Li, Yukun Zheng, Chaorui Zhang, SIYI LIN, Fei Teng, Hongjun Yang, Ming Chen, Steve Xie, Ruihai Wu
AI summary
Problem
Existing simulators struggle to accurately model diverse deformable objects like garments and food in realistic household settings, hindering the development of robust robotic policies and reliable sim-to-real transfer.
Approach
LeHome integrates specialized physics engines for six deformable object categories, introduces an Action Graph mechanism to enforce causal interaction logic, and combines teleoperation data collection with domain randomization to train policies for low-cost robotic platforms.
Key results
- High-fidelity simulation of six deformable object categories using tailored physics engines
- Action Graph mechanism for modeling causal, state-changing interactions like cutting and pouring
- Seamless integration of low-cost open-source robots alongside industrial manipulators
- Effective sim-to-real transfer and policy learning across six diverse household tasks using domain randomization
Why it matters
Provides a scalable, realistic testbed that accelerates the development and deployment of household robots capable of handling complex, everyday deformable object tasks.
Abstract
Household environments present one of the most common, impactful yet challenging application domains for robotics. Within household scenarios, manipulating deformable objects is particularly difficult, both in simulation and real- world execution, due to varied categories and shapes, complex dynamics, and diverse material properties, as well as the lack of reliable deformable-object support in existing simulations. We introduce LeHome, a comprehensive simulation environment designed for deformable object manipulation in household scenarios. LeHome covers a wide spectrum of deformable objects, such as garments and food items, offering high-fidelity dynamics and realistic interactions that existing simulators struggle to simulate accurately. Moreover, LeHome supports multiple robotic embodiments and emphasizes low-cost robots as a core focus, enabling end-to-end evaluation of household tasks on resource-constrained hardware. By bridging the gap between realistic deformable object simulation and practical robotic platforms, LeHome provides a scalable testbed for advancing household robotics. Webpage: lehome-web.github.io/. ∗Corresponding author: Ruihai Wu, wuruihai@pku.edu.cn 1Peking University. 2Institute of Automation, Chinese Academy of Sciences. 3Lightwheel. 4The University of Hong Kong.