论文/arXiv 2610.20336·14 天前

AutoRSR：用于可扩展机器人学习的自动化 Real-to-Sim-to-Real 数据生成

AutoRSR将扫描的真实工作空间自动转为仿真资产并生成操作数据，在三项真机操作任务上验证。

AI 整理

• 本体 SDK 与控制
• 仿真与训练
• 数据与采集

原文链接：AutoRSR: Automated Real-to-Sim-to-Real Data Generation for Scalable Robot Learning（arXiv 2610.20336 · 发布日期：2026-10-14）

AutoRSR: Automated Real-to-Sim-to-Real Data Generation for Scalable Robot Learning

AutoRSR将扫描的真实工作空间自动转为仿真资产并生成操作数据，在三项真机操作任务上验证。

核心要点

• 真实演示采集耗费人力和机器人时间，仿真环境构建仍需大量手工处理。
• AutoRSR由多视角观测、机器人状态和开放词汇查询重建并配准工作空间。
• 从少量参考动作出发，结合轨迹插值和域随机化生成可执行操作轨迹。
• 每任务1K自动生成片段训练的策略在真机成功率达73.3--86.7%。

验证范围与局限：摘要报告的验证范围为三个真实世界操作任务。

英文摘要 (Abstract)

Scaling embodied robot learning requires large and diverse manipulation datasets, but collecting real-world demonstrations remains expensive in human effort and robot time. Simulation provides a scalable alternative, yet converting a real workspace into a robot-learning-ready environment still requires substantial manual effort for object extraction, asset processing, coordinate calibration, and trajectory specification. We present AutoRSR, a highly automated real-to-sim-to real framework that converts scanned real-world workspaces into reusable embodied simulation assets and scalable manipulation data. Given multi-view observations, robot states, and open-vocabulary semantic queries, AutoRSR reconstructs the workspace, extracts individual object assets, and automatically registers the reconstructed scene to the robot base frame at metric scale. Starting from a small number of reference motions, AutoRSR then generates executable manipulation trajectories and scales them through trajectory interpolation and domain randomization. After workspace scanning and semantic queries, the remaining pipeline requires no manual object annotation, scene-to-robot calibration, or robot teleoperation. Across three real-world manipulation tasks, policies trained on 1K automatically generated episodes per task achieve 73.3--86.7% real-world success rates, comparable to pi 0.5 trained from 150 human teleoperated demonstrations, while reducing the human time required for data generation by an order of magnitude. These results demonstrate that real-world observations can be converted into metrically aligned, executable, and scalable simulation data with substantially reduced human effort.

作者：Jiawei Zhang, Chang Liu, Litao Deng, Tao Zhang, Qin Jin

来源

本页事实对应的公开页面，以原文为准。

1. arXiv 2610.20336：AutoRSR: Automated Real-to-Sim-to-Real Data Generation for Scalable Robot Learning访问 2026-10-21