WorldContact: A Contact-Centric World Model for Scalable Robot Learning

2026-09-16

AI Summary

本文提出WorldContact模型，通过有限的高质量轨迹生成额外训练数据，以解决机器人适应新物体和任务时经验获取成本高的问题。

Abstract

Adapting robots to new objects and tasks requires interaction experience that can be costly to obtain. We present WorldContact, a contact-centric world model for deformable-object manipulation, constructed from a limited set of high-quality trajectories to generate additional training data efficiently. It predicts object dynamics using larger time steps than the source numerical simulator, which requires small integration steps to resolve rapid motion and prevent interpenetration. We evaluate WorldContact across 16 shopping-bag manipulation tasks. State-rollout measurements on a single H100 GPU show a $10\times$ speedup over the source simulator, excluding rendering and disk I/O. We use the generated data to fine-tune an existing vision-language-action policy and deploy it directly on a real robot. In bag lifting, the same policy achieves 65% single-attempt success when fine-tuned on source simulation data alone, compared with 95% when fine-tuned on the dataset expanded with WorldContact. These results support efficient data generation with WorldContact for robot policy adaptation.

Problem

• robot learning
• interaction experience
• training data generation
• deformable-object manipulation

Innovation

• contact-centric world model
• deformable-object manipulation
• data generation efficiency
• policy adaptation