# SimFoundry：面向策略学习与评估的模块化自动化场景生成系统

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-06-26 08:00
- AIHOT 分数：52
- AIHOT 链接：https://aihot.virxact.com/items/cmqylfgci02xxslivfgt04pkl
- 原文链接：https://arxiv.org/abs/2606.28276

## AI 摘要

SimFoundry是一个模块化自动化系统，能从视频零样本构建真实到仿真的场景，生成可用的数字孪生，并支持对象、场景和任务的编辑，自动生成保持原始功能但经过变化的数字表亲。基于SimFoundry数据训练的策略可零样本迁移到真实世界的多步操作、铰接物体交互和双手交互任务；数字表亲有助于泛化到新真实条件。在7个操作任务和5种策略架构上，SimFoundry仿真评估与真实性能高度相关（平均Pearson相关系数0.911，最大排序违反0.018）。使用对象、场景和任务表亲训练的仿真策略在零样本真实评测中，任务成功率分别提升17%、21%和40%。

## 正文

Training and evaluating robot policies in the real world is costly and difficult to scale. We introduce SimFoundry, a modular and automated system for zero-shot real-to-sim scene construction from a video. SimFoundry generates sim-ready digital twins and supports object, scene, and task editing, enabling the automated generation of diverse digital cousins: affordance-preserving variations of reconstructed real-world scenes. Policies trained on SimFoundry data transfer zero-shot to challenging real tasks involving multi-step manipulation, articulated object interaction, and bimanual interaction, and its digital cousins (variations of the original scene, objects, and tasks) facilitate generalization to new real-world conditions. Across 7 manipulation tasks and 5 policy architectures, SimFoundry simulation evaluations strongly predict real-world performance, with mean Pearson correlation 0.911 and mean maximum ranking violation 0.018. When evaluating sim-trained policies zero-shot in the real world, policies trained with object, scene, and task cousins in simulation show average task success rate improvements of 17%, 21%, and 40%, respectively. Additional details at https://research.nvidia.com/labs/gear/simfoundry/ .